docs: fix conflicting info regarding HTML and clarify

[dyc3]

Summary

fixes #3828

[netlify]

✅ Deploy Preview for biomejs ready!

Name	Link
🔨 Latest commit	d949879
🔍 Latest deploy log	https://app.netlify.com/projects/biomejs/deploys/696be82a6df4490007153f67
😎 Deploy Preview	https://deploy-preview-3829--biomejs.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.

[coderabbitai]

Walkthrough

This change clarifies HTML configuration: the HTML formatter is explicitly disabled by default while experimental. html.experimentalFullSupportEnabled now names HTML-ish languages (Vue, Svelte, Astro) and states embedded languages are parsed, formatted and linted consistently when enabled. Notes were added that when html.experimentalFullSupportEnabled is disabled, Biome will only extract JavaScript/TypeScript from HTML-ish files; the option does not affect plain .html files; and html.formatter.enabled must be enabled separately (it will default to enabled once the formatter is non‑experimental).

Suggested reviewers

• ematipico
• siketyan

🚥 Pre-merge checks | ✅ 4

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and concisely summarises the PR's primary change: fixing conflicting HTML documentation and clarifying configuration.
Description check	✅ Passed	The description relates to the changeset by linking to issue #3828, which directly motivates the documentation updates.
Linked Issues check	✅ Passed	The PR substantially addresses issue #3828's requirements by clarifying HTML formatter default state, distinguishing HTML-ish languages, and explaining html.experimentalFullSupportEnabled's scope.
Out of Scope Changes check	✅ Passed	All documentation changes are directly scoped to resolving the conflicting information and clarifications requested in issue #3828.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 2

🤖 Fix all issues with AI agents

In `@src/content/docs/reference/configuration.mdx`:
- Around line 1352-1353: Replace the non-canonical casing
"Javascript/Typescript" in the documentation text with the correct
"JavaScript/TypeScript" (look for the exact string "Javascript/Typescript" in
the sentence starting "When disabled, Biome will only extract the
Javascript/Typescript parts...") so the doc uses the standard capitalisation for
both names.
- Around line 1341-1357: Update the caution block text to accurately state that
only the HTML parser and formatter are disabled by default (not the linter);
change the sentence that currently reads "The HTML parser, formatter and linter
are **disabled** by default" to mention only "parser and formatter" and
optionally note that html.linter.enabled and html.assist.enabled default to
true; also correct the wording "Javascript/Typescript" to
"JavaScript/TypeScript" in the description of
html.experimentalFullSupportEnabled and ensure the note about enabling
html.formatter.enabled remains intact.

[coderabbitai]

⚠️ Potential issue | 🟠 Major

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

python - <<'PY'
import json, urllib.request

try:
    url = "https://biomejs.dev/schemas/2.3.11/schema.json"
    data = json.load(urllib.request.urlopen(url))
    
    def walk(node, path):
        if isinstance(node, dict):
            if "default" in node and "html" in path:
                print(".".join(path), "=", node["default"])
            for k, v in node.items():
                walk(v, path + [k])
        elif isinstance(node, list):
            for i, v in enumerate(node):
                walk(v, path + [str(i)])
    
    walk(data, [])
except Exception as e:
    print(f"Error fetching schema: {e}")
PY

Repository: biomejs/website

Length of output: 145

---

🏁 Script executed:

#!/bin/bash
set -euo pipefail

# Search for html configuration defaults in the repository
echo "=== Searching for html configuration defaults ==="
rg "html\.(linter|formatter|assist)\.enabled" --max-count 20 -B 2 -A 2

echo ""
echo "=== Searching for 'default' near html configuration ==="
rg "html\." src/content/docs/reference/configuration.mdx | head -30

echo ""
echo "=== Checking if there's a defaults section in configuration.mdx ==="
rg -A 5 -B 5 "default.*true|default.*false" src/content/docs/reference/configuration.mdx | grep -i html | head -40

Repository: biomejs/website

Length of output: 3571

---

🏁 Script executed:

#!/bin/bash
rg "html\.parser\.enabled" src/content/docs/reference/configuration.mdx -A 3 -B 3

Repository: biomejs/website

Length of output: 41

---

🏁 Script executed:

#!/bin/bash
sed -n '1330,1380p' src/content/docs/reference/configuration.mdx

Repository: biomejs/website

Length of output: 1410

---

🏁 Script executed:

#!/bin/bash
sed -n '1360,1375p' src/content/docs/reference/configuration.mdx

Repository: biomejs/website

Length of output: 398

---

🏁 Script executed:

#!/bin/bash
grep -n "html.linter.enabled" src/content/docs/reference/configuration.mdx -A 3

Repository: biomejs/website

Length of output: 145

---

🏁 Script executed:

#!/bin/bash
sed -n '1469,1480p' src/content/docs/reference/configuration.mdx

Repository: biomejs/website

Length of output: 230

---

The caution overstates what's disabled by default—the linter is actually enabled.

The caution claims the HTML parser, formatter, and linter are disabled by default, but html.linter.enabled has a default of true (as does html.assist.enabled). Update the caution to reflect that only the parser and formatter are disabled by default.

Minor fix: "Javascript/Typescript" (line 1352) should be "JavaScript/TypeScript".

🤖 Prompt for AI Agents

In `@src/content/docs/reference/configuration.mdx` around lines 1341 - 1357,
Update the caution block text to accurately state that only the HTML parser and
formatter are disabled by default (not the linter); change the sentence that
currently reads "The HTML parser, formatter and linter are **disabled** by
default" to mention only "parser and formatter" and optionally note that
html.linter.enabled and html.assist.enabled default to true; also correct the
wording "Javascript/Typescript" to "JavaScript/TypeScript" in the description of
html.experimentalFullSupportEnabled and ensure the note about enabling
html.formatter.enabled remains intact.