feat: add hoistDependencies
#1
Conversation
✅ Actions performedReview triggered.
|
WalkthroughThe changes introduce a new Changes
Sequence Diagram(s)sequenceDiagram
participant User
participant Nuxt
participant hoistDependencies
participant pkg-types
participant exsolve
User->>hoistDependencies: Call with (hoist: string[], nuxt?)
hoistDependencies->>Nuxt: Get Nuxt context and rootDir
hoistDependencies->>pkg-types: Read root package.json
hoistDependencies->>hoistDependencies: Filter out already declared packages
loop For each package to hoist
hoistDependencies->>exsolve: Resolve type path for package
end
hoistDependencies->>Nuxt: Merge resolved paths into Nitro tsConfig
hoistDependencies->>Nuxt: Hook into prepare:types to inject paths
Poem
✨ Finishing Touches
🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (3)
src/hoist.ts (3)
15-34: Consider improving error handling specificity.The function correctly handles the happy path and gracefully falls back to
nullon errors. However, the catch block silently swallows all errors, which might make debugging difficult.Consider logging errors or being more specific about which errors to catch:
} catch { return null; }Could be improved to:
} catch (error) { // Log for debugging purposes in development if (process.env.NODE_ENV === 'development') { console.debug(`Failed to resolve type path for ${path}:`, error); } return null; }
77-96: Consider documenting the side effects of configuration mutation.The function modifies Nuxt configuration objects in place, which could have unexpected side effects. While this appears to be the intended behavior, it should be documented.
Add JSDoc comments to clarify the behavior:
/** + * Hoists TypeScript type declarations for specified dependencies by configuring + * path mappings in Nuxt and Nitro TypeScript configurations. + * + * @param hoist - Array of package names to hoist + * @param nuxt - Nuxt instance (optional, uses current context if not provided) + * + * @remarks This function modifies the Nuxt configuration in place by setting + * TypeScript path mappings for better type resolution when shamefully-hoist=false. */ export async function hoistDependencies(hoist: string[], nuxt = useNuxt()) {
78-80: Verify defu usage with spread operator.The use of
{ ...paths }inside the defu merge might not be necessary sincepathsis already an object. This could lead to unnecessary object creation.Consider simplifying the defu usage:
nuxt.options.nitro.typescript = defu(nuxt.options.nitro.typescript, { - tsConfig: { compilerOptions: { paths: { ...paths } } }, + tsConfig: { compilerOptions: { paths } }, });Apply the same pattern to lines 86, 90, and 94.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
pnpm-lock.yamlis excluded by!**/pnpm-lock.yaml
📒 Files selected for processing (7)
.github/workflows/release.yml(2 hunks)README.md(0 hunks)package.json(1 hunks)src/hoist.ts(1 hunks)src/index.ts(1 hunks)tsconfig.json(2 hunks)tsdown.config.ts(1 hunks)
💤 Files with no reviewable changes (1)
- README.md
🔇 Additional comments (13)
.github/workflows/release.yml (2)
9-9: LGTM: Quote style standardization.The change from single to double quotes for the tag pattern is a good formatting standardization and doesn't affect functionality.
25-26: LGTM: Added proper file ending.Adding a newline at the end of the file follows good text file conventions.
tsconfig.json (3)
4-4: LGTM: Enhanced library support.Adding "dom" and "esnext" to the lib array expands the available JavaScript APIs, which is appropriate for the new hoisting functionality.
9-9: LGTM: Node.js types support.Adding "@types/node" to the types array aligns with the new devDependency declared in package.json and supports Node.js APIs used in the implementation.
18-18: LGTM: Clean include configuration.The single-line format for the include array is cleaner and appropriately includes both source and test directories.
tsdown.config.ts (3)
1-1: LGTM: Quote style consistency.Standardizing on double quotes improves consistency across the configuration file.
4-4: LGTM: Explicit entry point configuration.Specifying the exact entry file
./src/index.tsis more explicit and aligns with the updated export structure.
5-6: LGTM: Improved formatting.The formatting improvements with consistent quotes and trailing semicolon enhance code quality.
package.json (2)
37-37: LGTM: Node.js types support.Adding
@types/nodeas a devDependency aligns with the TypeScript configuration updates and provides proper type support for Node.js APIs.
42-45: LGTM: Proper peer dependency configuration for Nuxt module.Moving
@nuxt/kitand adding@nuxt/schemaas peer dependencies is the correct approach for a Nuxt module. The version ranges support both Nuxt 3.16+ and Nuxt 4 RC, providing good compatibility.src/hoist.ts (3)
1-9: LGTM! Clean and well-organized imports.The imports are properly structured and include all necessary dependencies for the functionality implemented in this module.
44-48: LGTM! Robust dependency collection logic.The regular expression correctly identifies nested packages, and the Set-based approach efficiently combines dependencies from both
dependenciesanddevDependencies.
53-61: LGTM! Correct handling of scoped and nested packages.The logic properly parses scoped packages and correctly skips packages that already exist in package.json dependencies.
| "dependencies": { | ||
| "defu": "^6.1.4", | ||
| "exsolve": "^1.0.7", | ||
| "magic-string": "^0.30.17", | ||
| "pathe": "^2.0.3", | ||
| "pkg-types": "^2.2.0", | ||
| "unplugin": "^2.3.5" | ||
| } |
There was a problem hiding this comment.
💡 Verification agent
🧩 Analysis chain
Verify runtime dependencies are utilized.
The new runtime dependencies appear to support the hoistDependencies functionality, but let's verify they are actually used in the implementation.
🏁 Script executed:
#!/bin/bash
# Verify that all declared dependencies are actually used in the source code
echo "Checking usage of runtime dependencies:"
for dep in "defu" "exsolve" "magic-string" "pathe" "pkg-types" "unplugin"; do
echo "=== Checking $dep ==="
rg -l "from ['\"]$dep['\"]|require\(['\"]$dep['\"]" src/
doneLength of output: 1400
Unused runtime dependencies detected
The following packages are declared in package.json but not imported or required anywhere in src/hoist.ts (or elsewhere in src/):
- magic-string
- unplugin
Please either remove these entries from your dependencies or add the necessary import/use statements to your implementation.
🤖 Prompt for AI Agents
In package.json lines 46 to 53, the dependencies "magic-string" and "unplugin"
are declared but not used anywhere in the src/ directory, including
src/hoist.ts. To fix this, either remove these two packages from the
dependencies list if they are not needed, or add appropriate import statements
and usage of these packages in the source code where required.
| export async function hoistDependencies(hoist: string[], nuxt = useNuxt()) { | ||
| const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch( | ||
| () => ({}) as PackageJson, | ||
| ); | ||
| const NESTED_PKG_RE = /^[^@]+\//; | ||
| const dependencies = new Set([ | ||
| ...Object.keys(packageJSON.dependencies || {}), | ||
| ...Object.keys(packageJSON.devDependencies || {}), | ||
| ]); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Improve error handling for package.json reading.
The current error handling hides all errors when reading package.json, which could mask important issues like permission problems or malformed JSON.
Consider being more specific about error handling:
const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch(
- () => ({}) as PackageJson,
+ (error) => {
+ if (error.code === 'ENOENT') {
+ return {} as PackageJson;
+ }
+ throw error; // Re-throw other errors like permission issues or malformed JSON
+ },
);📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| export async function hoistDependencies(hoist: string[], nuxt = useNuxt()) { | |
| const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch( | |
| () => ({}) as PackageJson, | |
| ); | |
| const NESTED_PKG_RE = /^[^@]+\//; | |
| const dependencies = new Set([ | |
| ...Object.keys(packageJSON.dependencies || {}), | |
| ...Object.keys(packageJSON.devDependencies || {}), | |
| ]); | |
| export async function hoistDependencies(hoist: string[], nuxt = useNuxt()) { | |
| const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch( | |
| (error) => { | |
| if (error.code === 'ENOENT') { | |
| return {} as PackageJson; | |
| } | |
| throw error; // Re-throw other errors like permission issues or malformed JSON | |
| }, | |
| ); | |
| const NESTED_PKG_RE = /^[^@]+\//; | |
| const dependencies = new Set([ | |
| ...Object.keys(packageJSON.dependencies || {}), | |
| ...Object.keys(packageJSON.devDependencies || {}), | |
| ]); | |
| } |
🤖 Prompt for AI Agents
In src/hoist.ts around lines 40 to 48, the current catch block for reading
package.json suppresses all errors, potentially hiding critical issues. Modify
the error handling to catch only expected errors like file-not-found, and
rethrow or log unexpected errors such as permission issues or malformed JSON.
This can be done by checking the error type or code inside the catch block and
handling accordingly to avoid masking important problems.
| const paths = Object.fromEntries( | ||
| await Promise.all( | ||
| hoist.map(async (pkg) => { | ||
| const [_pkg = pkg, _subpath] = NESTED_PKG_RE.test(pkg) | ||
| ? pkg.split("/") | ||
| : [pkg]; | ||
| const subpath = _subpath ? "/" + _subpath : ""; | ||
|
|
||
| // ignore packages that exist in `package.json` as these can be resolved by TypeScript | ||
| if (dependencies?.has(_pkg)) { | ||
| return []; | ||
| } | ||
|
|
||
| const path = await resolveTypePath( | ||
| _pkg + subpath, | ||
| subpath, | ||
| nuxt.options.modulesDir, | ||
| ); | ||
| if (path) { | ||
| return [[pkg, [path]]]; | ||
| } | ||
|
|
||
| return []; | ||
| }), | ||
| ).then((r) => r.flat()), | ||
| ); |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add input validation for the hoist parameter.
The function doesn't validate the input hoist array, which could lead to runtime errors if invalid values are passed.
Add input validation at the beginning of the function:
export async function hoistDependencies(hoist: string[], nuxt = useNuxt()) {
+ if (!Array.isArray(hoist)) {
+ throw new TypeError('hoist parameter must be an array of strings');
+ }
+
+ if (hoist.some(pkg => typeof pkg !== 'string' || !pkg.trim())) {
+ throw new TypeError('All hoist entries must be non-empty strings');
+ }
+
const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch(🤖 Prompt for AI Agents
In src/hoist.ts between lines 50 and 75, the hoist parameter is used without
validation, risking runtime errors if invalid values are passed. Add input
validation at the start of the function to check that hoist is an array and that
each element is a non-empty string. If the validation fails, throw an
appropriate error or handle it gracefully to prevent further processing with
invalid input.
commit: |
There was a problem hiding this comment.
Actionable comments posted: 4
♻️ Duplicate comments (2)
src/hoist.ts (2)
35-35: Fix error handling for package.json reading (addresses past feedback).This issue was previously identified but not yet addressed. The current error handling hides all errors when reading package.json, which could mask important issues like permission problems or malformed JSON.
Apply this fix to be more specific about error handling:
const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch( - () => ({}) as PackageJson, + (error) => { + if (error.code === 'ENOENT') { + return {} as PackageJson; + } + throw error; // Re-throw other errors like permission issues or malformed JSON + }, );
34-34: Add input validation for the hoist parameter (addresses past feedback).This issue was previously identified but not yet addressed. The function doesn't validate the input
hoistarray, which could lead to runtime errors if invalid values are passed.Add input validation at the beginning of the function:
export async function hoistDependencies(hoist: string[], nuxt = useNuxt()) { + if (!Array.isArray(hoist)) { + throw new TypeError('hoist parameter must be an array of strings'); + } + + if (hoist.some(pkg => typeof pkg !== 'string' || !pkg.trim())) { + throw new TypeError('All hoist entries must be non-empty strings'); + } + const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch(
🧹 Nitpick comments (6)
scripts/switch-nuxt.sh (2)
1-2: Prefer portable she-bang and stricter error flags
#!/bin/shoften maps to different shells (e.g.dashon Debian,bashon macOS). Using/usr/bin/envis more portable, and adding-u/-o pipefailtightens error handling.-#!/bin/sh -set -e +#!/usr/bin/env sh +set -euo pipefail
2-2: Fail fast whenpnpmis missingA quick availability check gives a clearer error than a cryptic “command not found”.
set -e +command -v pnpm >/dev/null 2>&1 || { + echo "❌ pnpm is required but not installed." >&2 + exit 1 +}.github/workflows/preview-release.yml (2)
24-31: Pin reusable actions to commit SHAs for supply-chain safety.
actions/checkout@v4andactions/setup-node@v4are mutable tags.
Consistency and SBOM requirements generally mandate pinning to a specific
commit hash (as you already did forpnpm/action-setup).Example:
-uses: actions/checkout@v4 +uses: actions/[email protected] # 2f4e... (pin to commit)Apply the same pattern to
actions/setup-node.
27-27: Explicitly set the pnpm version for deterministic builds.
pnpm/action-setupdefaults to the latest release, which may introduce
breaking changes unexpectedly. Add theversioninput to lock the toolchain:-uses: pnpm/action-setup@a7487c7e89a18df4991f7f222e4898a00d66ddda +uses: pnpm/action-setup@a7487c7e89a18df4991f7f222e4898a00d66ddda +with: + version: 8.10.0 # keep in sync with packageManager fieldsrc/hoist.ts (2)
13-28: Consider improving error handling specificity.The
resolveTypePathfunction correctly handles the module resolution logic, but the catch block on line 25 silently swallows all errors. While returningnullfor resolution failures is appropriate, consider logging unexpected errors for debugging purposes.} catch { + // Consider logging unexpected errors for debugging return null; }
49-49: Remove unnecessary optional chaining.The
dependenciesvariable is always defined as a Set on line 37, so the optional chaining is unnecessary here.- if (dependencies?.has(_pkg)) { + if (dependencies.has(_pkg)) {
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
⛔ Files ignored due to path filters (1)
pnpm-lock.yamlis excluded by!**/pnpm-lock.yaml
📒 Files selected for processing (5)
.github/workflows/preview-release.yml(1 hunks).gitignore(1 hunks)package.json(2 hunks)scripts/switch-nuxt.sh(1 hunks)src/hoist.ts(1 hunks)
✅ Files skipped from review due to trivial changes (1)
- .gitignore
🚧 Files skipped from review as they are similar to previous changes (1)
- package.json
🧰 Additional context used
🧬 Code Graph Analysis (1)
src/hoist.ts (1)
src/index.ts (1)
hoistDependencies(1-1)
🔇 Additional comments (2)
src/hoist.ts (2)
1-7: LGTM! Clean imports and version detection.The imports are well-organized and the Nuxt version detection is straightforward and effective.
63-79: LGTM! Proper TypeScript configuration handling.The function correctly configures TypeScript paths for both Nitro and Nuxt, with appropriate version-specific handling for Nuxt v4. The use of
defufor deep merging ensures existing configurations are preserved.
| # Default to 'latest' if no argument is provided | ||
| VERSION=${1:-latest} | ||
|
|
||
| echo "Switching to nuxt version: $VERSION" | ||
| pnpm i nuxt@$VERSION @nuxt/kit@$VERSION @nuxt/schema@$VERSION No newline at end of file |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Harden the install step & keep package.json clean
- Quote
$VERSIONto avoid word-splitting or globbing surprises. pnpm iadds runtime deps; for a module that only needs Nuxt for local testing you probably want dev deps:pnpm add -D.- If you really need them in
peerDependencies, add the--save-peerflag instead of mutatingdependencies.
-echo "Switching to nuxt version: $VERSION"
-pnpm i nuxt@$VERSION @nuxt/kit@$VERSION @nuxt/schema@$VERSION
+echo "Switching to Nuxt version: $VERSION"
+# Installs as devDependencies, keeps runtime deps slim.
+pnpm add -D "nuxt@${VERSION}" "@nuxt/kit@${VERSION}" "@nuxt/schema@${VERSION}"🤖 Prompt for AI Agents
In scripts/switch-nuxt.sh around lines 4 to 8, the script installs Nuxt packages
without quoting the version variable, risking word-splitting or globbing issues.
Also, it uses 'pnpm i' which adds runtime dependencies, but since Nuxt is likely
needed only for local testing, these should be added as dev dependencies using
'pnpm add -D'. If the packages are intended as peer dependencies, use the
'--save-peer' flag instead of modifying dependencies directly. Update the
install command to quote $VERSION and use the appropriate pnpm flags
accordingly.
|
|
||
| jobs: | ||
| release: | ||
| if: ${{ contains(github.event.pull_request.labels.*.name, 'cr-tracked') }} |
There was a problem hiding this comment.
🛠️ Refactor suggestion
if expression can break on push events.
For non-PR events (push), github.event.pull_request is null, so
contains(github.event.pull_request.labels.*.name, 'cr-tracked') throws a
runtime evaluation error and cancels the job.
Guard the check with an event-type predicate:
-if: ${{ contains(github.event.pull_request.labels.*.name, 'cr-tracked') }}
+if: ${{ github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, 'cr-tracked') }}📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| if: ${{ contains(github.event.pull_request.labels.*.name, 'cr-tracked') }} | |
| if: ${{ github.event_name == 'pull_request' && contains(github.event.pull_request.labels.*.name, 'cr-tracked') }} |
🤖 Prompt for AI Agents
In .github/workflows/preview-release.yml at line 19, the current if expression
assumes github.event.pull_request exists, which causes runtime errors on push
events where it is null. To fix this, add a guard condition to first check that
the event is a pull_request before accessing pull_request.labels. Modify the if
expression to ensure it only evaluates contains(...) when the event is a
pull_request, preventing errors on push events.
| tags: | ||
| - '!**' |
There was a problem hiding this comment.
Invalid negation pattern for pushed tags – switch to tags-ignore.
push.tags does not support negation ('!**'). Use tags-ignore (or omit the block entirely) to prevent tag-triggered runs, otherwise the workflow will fail to parse.
- tags:
- - '!**'
+ tags-ignore:
+ - '**'🤖 Prompt for AI Agents
In .github/workflows/preview-release.yml at lines 6 to 7, the tags field uses an
invalid negation pattern '!**' which is not supported for push tags. To fix
this, remove the tags block entirely or replace it with a tags-ignore block to
exclude all tags from triggering the workflow. This change will prevent parsing
errors and correctly ignore tag pushes.
There was a problem hiding this comment.
Actionable comments posted: 1
♻️ Duplicate comments (3)
src/hoist.ts (3)
40-40: Add input validation for the hoist parameter.The function doesn't validate the input
hoistarray, which could lead to runtime errors if invalid values are passed.Add input validation at the beginning of the function:
export async function hoistDependencies(hoist: string[], nuxt = useNuxt()) { + if (!Array.isArray(hoist)) { + throw new TypeError('hoist parameter must be an array of strings'); + } + + if (hoist.some(pkg => typeof pkg !== 'string' || !pkg.trim())) { + throw new TypeError('All hoist entries must be non-empty strings'); + } + const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch(
41-41: Improve error handling for package.json reading.The current error handling hides all errors when reading package.json, which could mask important issues like permission problems or malformed JSON.
Consider being more specific about error handling:
const packageJSON = await readPackageJSON(nuxt.options.rootDir).catch( - () => ({}) as PackageJson, + (error) => { + if (error.code === 'ENOENT') { + return {} as PackageJson; + } + throw error; // Re-throw other errors like permission issues or malformed JSON + }, );
42-42: Clarify regex name and improve logic.The regex
NESTED_PKG_REname is misleading. It's actually checking for packages with subpaths (likelodash/debounce), not nested packages. The pattern/^[^@]+\//also won't work correctly for scoped packages with subpaths like@vue/test-utils/subpath.- const NESTED_PKG_RE = /^[^@]+\//; + const SUBPATH_PKG_RE = /\//;And update the usage on line 51:
- const [_pkg = pkg, _subpath] = NESTED_PKG_RE.test(pkg) ? pkg.split("/") : [pkg]; + const [_pkg = pkg, _subpath] = SUBPATH_PKG_RE.test(pkg) ? pkg.split("/", 2) : [pkg];This will correctly handle both regular packages with subpaths (
lodash/debounce) and scoped packages with subpaths (@vue/test-utils/subpath).
🧹 Nitpick comments (4)
src/hoist.ts (4)
55-55: Remove unnecessary optional chaining.The optional chaining operator is unnecessary here since
dependenciesis always aSetinstance.- if (dependencies?.has(_pkg)) { + if (dependencies.has(_pkg)) {
70-72: Optimize object spreading for paths.The current object spreading of
pathscreates a new object unnecessarily. Usepathsdirectly since it's already the desired structure.nuxt.options.nitro.typescript = defu(nuxt.options.nitro.typescript, { - tsConfig: { compilerOptions: { paths: { ...paths } } }, + tsConfig: { compilerOptions: { paths } }, });
77-79: Optimize object spreading for paths (consistency).Apply the same optimization as suggested for the Nitro configuration to maintain consistency.
opts.tsConfig.compilerOptions = defu(opts.tsConfig.compilerOptions, { - paths: { ...paths }, + paths, });
82-83: Optimize object spreading for paths (Nuxt v4 configs).Apply the same optimization to the Nuxt v4 configurations for consistency.
- opts.nodeTsConfig.compilerOptions = defu(opts.nodeTsConfig.compilerOptions, { paths: { ...paths } }); - opts.sharedTsConfig.compilerOptions = defu(opts.sharedTsConfig.compilerOptions, { paths: { ...paths } }); + opts.nodeTsConfig.compilerOptions = defu(opts.nodeTsConfig.compilerOptions, { paths }); + opts.sharedTsConfig.compilerOptions = defu(opts.sharedTsConfig.compilerOptions, { paths });
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
README.md(1 hunks)src/hoist.ts(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- README.md
🔇 Additional comments (1)
src/hoist.ts (1)
1-7: LGTM: Clean imports and version detection.The imports are well-organized and the Nuxt version detection is straightforward and effective.
| /** | ||
| * @see [Nuxt source](https://github.com/nuxt/nuxt/blob/a0f9ddfe241bcf555f6305aa10c087a1fe64af87/packages/nuxt/src/core/utils/types.ts#L6) | ||
| */ | ||
| async function resolveTypePath(path: string, subpath: string, searchPaths = tryUseNuxt()?.options.modulesDir) { |
There was a problem hiding this comment.
🛠️ Refactor suggestion
Add null check for searchPaths parameter.
The searchPaths parameter could be undefined when tryUseNuxt() returns null, which would cause searchPaths?.map() to return undefined and potentially cause issues in resolveModulePath.
-async function resolveTypePath(path: string, subpath: string, searchPaths = tryUseNuxt()?.options.modulesDir) {
+async function resolveTypePath(path: string, subpath: string, searchPaths = tryUseNuxt()?.options.modulesDir || []) {📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
| async function resolveTypePath(path: string, subpath: string, searchPaths = tryUseNuxt()?.options.modulesDir) { | |
| async function resolveTypePath( | |
| path: string, | |
| subpath: string, | |
| searchPaths = tryUseNuxt()?.options.modulesDir || [] | |
| ) { |
🤖 Prompt for AI Agents
In src/hoist.ts at line 12, the searchPaths parameter may be undefined if
tryUseNuxt() returns null, leading to errors when calling searchPaths?.map().
Add a null check to ensure searchPaths is defined before using it, or provide a
default empty array to avoid passing undefined to resolveModulePath.
Summary by CodeRabbit
New Features
Bug Fixes
Chores
.gitignoreto exclude environment variable files.Refactor