bun test dots reporter #22919
bun test dots reporter #22919
Conversation
|
Updated 4:58 PM PT - Oct 3rd, 2025
❌ @pfgithub, your commit c2b05c5 has 3 failures in
🧪 To try this PR locally: bunx bun-pr 22919That installs a local version of the PR into your bun-22919 --bun |
Resolved conflicts in Arguments.zig by: - Keeping dots reporter support from pfg/dots - Adding max-concurrency parameter from origin/main - Updating help text to mention both junit and dots reporters
- Print newline before failure output when previous output was a dot - Add bunfig.toml support for dots reporter via test.reporter.dots config - Suppress failure list at end when using dots reporter (avoid redundant output) This improves the dots reporter UX by: 1. Preventing failure details from appearing on the same line as dots 2. Allowing users to set dots as their default reporter in bunfig.toml 3. Reducing noise by not re-listing failures when using compact dots format
- Adds new CLI flag --dots to enable the dots reporter - Works as a convenient shorthand for --reporter=dots - Complements existing bunfig.toml dots reporter option - Documentation is automatically included in help text 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
WalkthroughReplace the single file-based test reporter with a structured Changes
Possibly related PRs
Suggested reviewers
Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✨ Finishing touches🧪 Generate unit tests (beta)
📜 Recent review detailsConfiguration used: CodeRabbit UI Review profile: CHILL Plan: Pro Disabled knowledge base sources:
📒 Files selected for processing (1)
🧰 Additional context used📓 Path-based instructions (2)src/**/*.zig📄 CodeRabbit inference engine (.cursor/rules/building-bun.mdc)
Files:
**/*.zig📄 CodeRabbit inference engine (.cursor/rules/javascriptcore-class.mdc)
Files:
🧠 Learnings (1)📚 Learning: 2025-09-08T04:44:59.101ZApplied to files:
🔇 Additional comments (7)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
Disabled knowledge base sources:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (7)
src/bun.js/test/jest.zig(1 hunks)src/bunfig.zig(1 hunks)src/cli.zig(1 hunks)src/cli/Arguments.zig(2 hunks)src/cli/test_command.zig(8 hunks)test/js/bun/test/dots.fixture.ts(1 hunks)test/js/bun/test/dots.test.ts(1 hunks)
🧰 Additional context used
📓 Path-based instructions (11)
src/**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/building-bun.mdc)
Implement debug logs in Zig using
const log = bun.Output.scoped(.${SCOPE}, false);and invokinglog("...", .{})
Files:
src/bun.js/test/jest.zigsrc/bunfig.zigsrc/cli.zigsrc/cli/Arguments.zigsrc/cli/test_command.zig
**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/javascriptcore-class.mdc)
**/*.zig: Declare the extern C symbol in Zig and export a Zig-friendly alias for use
Wrap the Bun____toJS extern in a Zig method that takes a JSGlobalObject and returns JSC.JSValue
**/*.zig: Format Zig files with zig-format (bun run zig-format)
In Zig, manage memory carefully with allocators and use defer for cleanup
Files:
src/bun.js/test/jest.zigsrc/bunfig.zigsrc/cli.zigsrc/cli/Arguments.zigsrc/cli/test_command.zig
src/bun.js/**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/zig-javascriptcore-classes.mdc)
src/bun.js/**/*.zig: In Zig binding structs, expose generated bindings via pub const js = JSC.Codegen.JS and re-export toJS/fromJS/fromJSDirect
Constructors and prototype methods should return bun.JSError!JSC.JSValue to integrate Zig error handling with JS exceptions
Use parameter name globalObject (not ctx) and accept (*JSC.JSGlobalObject, *JSC.CallFrame) in binding methods/constructors
Implement getters as get(this, globalObject) returning JSC.JSValue and matching the .classes.ts interface
Provide deinit() for resource cleanup and finalize() that calls deinit(); use bun.destroy(this) or appropriate destroy pattern
Access JS call data via CallFrame (argument(i), argumentCount(), thisValue()) and throw errors with globalObject.throw(...)
For properties marked cache: true, use the generated Zig accessors (NameSetCached/GetCached) to work with GC-owned values
In finalize() for objects holding JS references, release them using .deref() before destroy
Files:
src/bun.js/test/jest.zig
test/**
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place all tests under the test/ directory
Files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
test/js/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place JavaScript and TypeScript tests under test/js/
Files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
test/js/bun/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place Bun API tests under test/js/bun/, separated by category (e.g., test/js/bun/glob/)
Files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
test/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
test/**/*.{js,ts}: Write tests in JavaScript or TypeScript using Bun’s Jest-style APIs (test, describe, expect) and run with bun test
Prefer data-driven tests (e.g., test.each) to reduce boilerplate
Use shared utilities from test/harness.ts where applicable
Files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
test/js/**
📄 CodeRabbit inference engine (test/CLAUDE.md)
Organize unit tests for specific features under
test/js/by module
Files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
**/*.{js,ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Format JavaScript/TypeScript files with Prettier (bun run prettier)
Files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
test/**/*.test.ts
📄 CodeRabbit inference engine (test/CLAUDE.md)
test/**/*.test.ts: Name test files*.test.tsand usebun:test
Do not write flaky tests: never wait for arbitrary time; wait for conditions instead
Never hardcode port numbers in tests; useport: 0to get a random port
When spawning Bun in tests, usebunExe()andbunEnvfromharness
Preferasync/awaitin tests; for a single callback, usePromise.withResolvers()
Do not set explicit test timeouts; rely on Bun’s built-in timeouts
UsetempDir/tempDirWithFilesfromharnessfor temporary files and directories in tests
For large/repetitive strings in tests, preferBuffer.alloc(count, fill).toString()over"A".repeat(count)
Import common test utilities fromharness(e.g.,bunExe,bunEnv,tempDirWithFiles,tmpdirSync, platform checks, GC helpers)
In error tests, assert non-zero exit codes for failing processes and usetoThrowfor synchronous errors
Usedescribeblocks for grouping,describe.eachfor parameterized tests, snapshots withtoMatchSnapshot, and lifecycle hooks (beforeAll,beforeEach,afterEach); track resources for cleanup inafterEach
Useusing/await usingwith Bun resources (e.g., Bun.listen/connect/spawn/serve) to ensure cleanup in tests
Files:
test/js/bun/test/dots.test.ts
test/**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
test/**/*.test.{ts,tsx}: Test files must be placed under test/ and end with .test.ts or .test.tsx
In tests, always use port: 0; do not hardcode ports or use custom random port functions
In tests, use normalizeBunSnapshot when asserting snapshots
Never write tests that merely assert absence of "panic" or "uncaught exception" in output
Avoid shell commands (e.g., find, grep) in tests; use Bun.Glob and built-ins instead
Prefer snapshot tests over exact stdout equality assertions
Files:
test/js/bun/test/dots.test.ts
🧠 Learnings (12)
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/**/*.{js,ts} : Write tests in JavaScript or TypeScript using Bun’s Jest-style APIs (test, describe, expect) and run with bun test
Applied to files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/js/bun/**/*.{js,ts} : Place Bun API tests under test/js/bun/, separated by category (e.g., test/js/bun/glob/)
Applied to files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/**/*.{js,ts} : Prefer data-driven tests (e.g., test.each) to reduce boilerplate
Applied to files:
test/js/bun/test/dots.fixture.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : Name test files `*.test.ts` and use `bun:test`
Applied to files:
test/js/bun/test/dots.fixture.tstest/js/bun/test/dots.test.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*-fixture.ts : Name test fixture files that are spawned by tests with the suffix `-fixture.ts`
Applied to files:
test/js/bun/test/dots.fixture.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : When spawning Bun in tests, use `bunExe()` and `bunEnv` from `harness`
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-09-08T04:44:59.101Z
Learnt from: CR
PR: oven-sh/bun#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-08T04:44:59.101Z
Learning: Applies to test/**/*.test.{ts,tsx} : In tests, use normalizeBunSnapshot when asserting snapshots
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/cli/**/*.{js,ts} : When testing Bun as a CLI, use spawn with bunExe() and bunEnv from harness, and capture stdout/stderr via pipes
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : Import common test utilities from `harness` (e.g., `bunExe`, `bunEnv`, `tempDirWithFiles`, `tmpdirSync`, platform checks, GC helpers)
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-09-20T03:39:41.770Z
Learnt from: pfgithub
PR: oven-sh/bun#22534
File: test/regression/issue/21830.fixture.ts:14-63
Timestamp: 2025-09-20T03:39:41.770Z
Learning: Bun's test runner supports async describe callbacks, unlike Jest/Vitest where describe callbacks must be synchronous. The syntax `describe("name", async () => { ... })` is valid in Bun.
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:09:39.100Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/dev-server-tests.mdc:0-0
Timestamp: 2025-08-30T00:09:39.100Z
Learning: Applies to test/bake/bake-harness.ts : Provide and maintain shared test utilities: devTest, prodTest, devAndProductionTest, Dev, Client, and helpers in the harness
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-09-08T04:44:59.101Z
Learnt from: CR
PR: oven-sh/bun#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-08T04:44:59.101Z
Learning: Applies to test/**/*.test.{ts,tsx} : Avoid shell commands (e.g., find, grep) in tests; use Bun.Glob and built-ins instead
Applied to files:
test/js/bun/test/dots.test.ts
🧬 Code graph analysis (1)
test/js/bun/test/dots.test.ts (1)
test/harness.ts (2)
bunExe(103-106)normalizeBunSnapshot(1809-1840)
🔇 Additional comments (7)
test/js/bun/test/dots.test.ts (1)
1-54: LGTM!The test implementation follows all coding guidelines:
- Uses
bun:testAPIs with async/await- Spawns Bun subprocess with
bunExe()andbunEnvfrom harness- Uses
normalizeBunSnapshotfor snapshot assertions- Validates the new
--dotsreporter flag behavior correctlytest/js/bun/test/dots.fixture.ts (1)
1-4: LGTM!The fixture appropriately uses
test.eachto generate parameterized tests across different test states (passing, skipped, failing, todo), which aligns with the coding guideline to prefer data-driven tests to reduce boilerplate. The 40 total tests (10 of each type) match the expectations indots.test.ts.src/bun.js/test/jest.zig (1)
457-464: LGTM!The condition correctly checks the new
reporters.junitflag instead of the deprecatedfile_reporterenum. This aligns with the broader refactor to support multiple reporters (dots and junit) and maintains the correct behavior of capturing test line numbers only when the junit reporter is enabled.src/cli.zig (1)
355-360: LGTM!The structural change from a single
file_reporterenum to a nestedreportersstruct with boolean flags (dotsandjunit) supports the new multiple-reporter capability. This design allows enabling both reporters simultaneously if needed in the future, while preserving thereporter_outfilefield for output path configuration.src/bunfig.zig (1)
242-255: LGTM!The bunfig parser correctly handles the new reporters structure:
- Sets
reporters.junit = truewhen a junit output path is specified- Parses
reporters.dotsas a boolean flag- Preserves
reporter_outfilefor the junit XML output path- Includes proper type validation for the dots boolean
The changes align with the broader refactor across the codebase and maintain backward compatibility for the junit reporter configuration.
src/cli/Arguments.zig (2)
207-210: LGTM!The help text and parameter definition correctly document both reporter options ("junit" and "dots") and provide the convenient
--dotsshorthand flag.
453-471: LGTM!The argument parsing logic correctly handles the new reporters structure:
- Enables
reporters.junitwhen--reporter=junitis specified, with proper validation requiring--reporter-outfile- Enables
reporters.dotswhen--reporter=dotsis specified, without requiring an outfile- Handles the
--dotsshorthand flag as an alias for--reporter=dots- Updates error messages to include both supported reporter formats
The implementation is clean and maintains consistency with the broader refactor.
There was a problem hiding this comment.
Actionable comments posted: 3
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
Disabled knowledge base sources:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
src/cli/test_command.zig(8 hunks)test/js/bun/test/dots.fixture.ts(1 hunks)test/js/bun/test/dots.test.ts(1 hunks)
🚧 Files skipped from review as they are similar to previous changes (1)
- test/js/bun/test/dots.test.ts
🧰 Additional context used
📓 Path-based instructions (8)
src/**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/building-bun.mdc)
Implement debug logs in Zig using
const log = bun.Output.scoped(.${SCOPE}, false);and invokinglog("...", .{})
Files:
src/cli/test_command.zig
**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/javascriptcore-class.mdc)
**/*.zig: Declare the extern C symbol in Zig and export a Zig-friendly alias for use
Wrap the Bun____toJS extern in a Zig method that takes a JSGlobalObject and returns JSC.JSValue
**/*.zig: Format Zig files with zig-format (bun run zig-format)
In Zig, manage memory carefully with allocators and use defer for cleanup
Files:
src/cli/test_command.zig
test/**
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place all tests under the test/ directory
Files:
test/js/bun/test/dots.fixture.ts
test/js/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place JavaScript and TypeScript tests under test/js/
Files:
test/js/bun/test/dots.fixture.ts
test/js/bun/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place Bun API tests under test/js/bun/, separated by category (e.g., test/js/bun/glob/)
Files:
test/js/bun/test/dots.fixture.ts
test/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
test/**/*.{js,ts}: Write tests in JavaScript or TypeScript using Bun’s Jest-style APIs (test, describe, expect) and run with bun test
Prefer data-driven tests (e.g., test.each) to reduce boilerplate
Use shared utilities from test/harness.ts where applicable
Files:
test/js/bun/test/dots.fixture.ts
test/js/**
📄 CodeRabbit inference engine (test/CLAUDE.md)
Organize unit tests for specific features under
test/js/by module
Files:
test/js/bun/test/dots.fixture.ts
**/*.{js,ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Format JavaScript/TypeScript files with Prettier (bun run prettier)
Files:
test/js/bun/test/dots.fixture.ts
🧠 Learnings (6)
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/**/*.{js,ts} : Write tests in JavaScript or TypeScript using Bun’s Jest-style APIs (test, describe, expect) and run with bun test
Applied to files:
test/js/bun/test/dots.fixture.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/js/bun/**/*.{js,ts} : Place Bun API tests under test/js/bun/, separated by category (e.g., test/js/bun/glob/)
Applied to files:
test/js/bun/test/dots.fixture.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : Name test files `*.test.ts` and use `bun:test`
Applied to files:
test/js/bun/test/dots.fixture.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*-fixture.ts : Name test fixture files that are spawned by tests with the suffix `-fixture.ts`
Applied to files:
test/js/bun/test/dots.fixture.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/**/*.{js,ts} : Prefer data-driven tests (e.g., test.each) to reduce boilerplate
Applied to files:
test/js/bun/test/dots.fixture.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : Use `describe` blocks for grouping, `describe.each` for parameterized tests, snapshots with `toMatchSnapshot`, and lifecycle hooks (`beforeAll`, `beforeEach`, `afterEach`); track resources for cleanup in `afterEach`
Applied to files:
test/js/bun/test/dots.fixture.ts
| var reporter = try ctx.allocator.create(CommandLineReporter); | ||
| defer { | ||
| if (reporter.file_reporter) |*file_reporter| { | ||
| switch (file_reporter.*) { | ||
| .junit => |junit_reporter| { | ||
| junit_reporter.deinit(); | ||
| }, | ||
| } | ||
| if (reporter.reporters.junit) |file_reporter| { | ||
| file_reporter.deinit(); | ||
| } | ||
| } |
There was a problem hiding this comment.
Destroy the allocated JUnit reporter after deinit.
JunitReporter.init() allocates the struct via bun.TrivialNew, so calling deinit() alone leaks that allocation. Add the corresponding bun.default_allocator.destroy(...) (and clear the optional) in the defer block to release the memory.
defer {
if (reporter.reporters.junit) |file_reporter| {
file_reporter.deinit();
+ bun.default_allocator.destroy(file_reporter);
+ reporter.reporters.junit = null;
}
}📝 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.
| var reporter = try ctx.allocator.create(CommandLineReporter); | |
| defer { | |
| if (reporter.file_reporter) |*file_reporter| { | |
| switch (file_reporter.*) { | |
| .junit => |junit_reporter| { | |
| junit_reporter.deinit(); | |
| }, | |
| } | |
| if (reporter.reporters.junit) |file_reporter| { | |
| file_reporter.deinit(); | |
| } | |
| } | |
| var reporter = try ctx.allocator.create(CommandLineReporter); | |
| defer { | |
| if (reporter.reporters.junit) |file_reporter| { | |
| file_reporter.deinit(); | |
| bun.default_allocator.destroy(file_reporter); | |
| reporter.reporters.junit = null; | |
| } | |
| } |
🤖 Prompt for AI Agents
In src/cli/test_command.zig around lines 1309 to 1314, the defer only calls
deinit() on the JUnit reporter but does not free the allocation made by
JunitReporter.init(), leaking memory; after calling file_reporter.deinit() call
bun.default_allocator.destroy(file_reporter) (or the appropriate destroy for the
allocator used) and clear the optional (set reporter.reporters.junit to
null/none) in the defer so the allocated struct is released and the optional is
cleared.
| test.each(Array.from({ length: 10 }, () => 0))("passing filterin", () => {}); | ||
| test.skip.each(Array.from({ length: 10 }, () => 0))("skipped filterin", () => {}); | ||
| test.failing("failing filterin", () => {}); | ||
| test("passing filterout", () => {}); | ||
| test.failing("failing filterin", () => {}); | ||
| test.failing("failing filterin", () => {}); | ||
| test.todo.each(Array.from({ length: 10 }, () => 0))("todo filterin", () => {}); |
There was a problem hiding this comment.
🧩 Analysis chain
Verify that the test API is properly imported.
The file uses test, test.each, test.skip, test.failing, and test.todo without an explicit import statement. Ensure that Bun's test runner automatically provides these APIs in fixture files, or add the required import.
Run the following script to check if other fixture files in the test suite include explicit imports:
🏁 Script executed:
#!/bin/bash
# Description: Check if other test fixture files include explicit imports for the test API.
# Search for fixture files and check their imports
fd -e ts -e js 'fixture' test/js/bun/test/ --exec head -5Length of output: 5653
Add missing Bun test import
At the top of test/js/bun/test/dots.fixture.ts add:
import { test } from "bun:test";🤖 Prompt for AI Agents
In test/js/bun/test/dots.fixture.ts lines 1 to 7, the file uses Bun test helpers
like test, test.each, test.skip, test.failing and test.todo but does not import
them; add the missing import statement at the top: import { test } from
"bun:test"; so the test symbol is defined for all uses in the file.
| test.failing("failing filterin", () => {}); | ||
| test("passing filterout", () => {}); | ||
| test.failing("failing filterin", () => {}); | ||
| test.failing("failing filterin", () => {}); |
There was a problem hiding this comment.
Eliminate duplicate test names.
Three tests share the identical name "failing filterin" (lines 3, 5, and 6). Duplicate test names can cause confusion in test output and may lead to issues with test identification and reporting.
Apply this diff to make the test names unique:
-test.failing("failing filterin", () => {});
+test.failing("failing filterin 1", () => {});
test("passing filterout", () => {});
-test.failing("failing filterin", () => {});
-test.failing("failing filterin", () => {});
+test.failing("failing filterin 2", () => {});
+test.failing("failing filterin 3", () => {});🤖 Prompt for AI Agents
In test/js/bun/test/dots.fixture.ts around lines 3 to 6, three tests share the
identical name "failing filterin"; rename the duplicate test titles so each is
unique (for example "failing filterin 1", "failing filterin 2", "failing
filterin 3" or more descriptive variants) and update any references if they are
used elsewhere, ensuring no two test() or test.failing() calls use the same
string.
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (1)
src/cli/test_command.zig (1)
1309-1314: ** Memory leak: destroy the allocated JUnit reporter after deinit.**
JunitReporter.init()at line 1343 allocates the struct viabun.TrivialNew(JunitReporter), which usesbun.default_allocator.create(). The defer block at lines 1311-1313 only callsdeinit()but does not destroy the allocation, causing a memory leak.Apply this diff to fix the leak:
defer { if (reporter.reporters.junit) |file_reporter| { file_reporter.deinit(); + bun.default_allocator.destroy(file_reporter); + reporter.reporters.junit = null; } }This matches the pattern used in
JunitReporterwhere allocations made withTrivialNewmust be explicitly destroyed.
🧹 Nitpick comments (1)
src/cli/test_command.zig (1)
715-828: Verify suite hierarchy logic and guard against infinite loops.The nested suite management for JUnit reporting is complex. Here are specific concerns:
Lines 758-765: The
while (current_suite_depth > needed_suites.items.len)loop closes suites but has a break condition that could leavecurrent_suite_depthout of sync if the guard at line 759 fails unexpectedly.Lines 785-793: Similar pattern in the suite closing loop - ensure
suites_to_closecounter correctly prevents infinite loops.Lines 802-806: The
while (describe_suite_index < needed_suites.items.len)loop appears safe as it always increments the index.Lines 724-727: The nested while loop condition
while (junit.suite_stack.items.len > 0 and !junit.suite_stack.items[junit.suite_stack.items.len - 1].is_file_suite)could infinite loop ifendTestSuite()fails to remove items from the stack.The logic appears sound for the happy path, but defensive checks could help prevent infinite loops in edge cases.
Consider adding iteration limits or assertions to guard against infinite loops:
while (current_suite_depth > needed_suites.items.len) { if (junit.suite_stack.items.len > 0 and !junit.suite_stack.items[junit.suite_stack.items.len - 1].is_file_suite) { bun.handleOom(junit.endTestSuite()); current_suite_depth -= 1; } else { + bun.debugAssert(current_suite_depth <= needed_suites.items.len); // Should have exited the loop break; } }Similarly for the other loops that modify suite state.
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
Disabled knowledge base sources:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (5)
src/bun.js/test/Execution.zig(1 hunks)src/bun.js/test/jest.zig(4 hunks)src/cli/test_command.zig(13 hunks)src/output.zig(1 hunks)test/js/bun/test/dots.test.ts(1 hunks)
🧰 Additional context used
📓 Path-based instructions (11)
src/**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/building-bun.mdc)
Implement debug logs in Zig using
const log = bun.Output.scoped(.${SCOPE}, false);and invokinglog("...", .{})
Files:
src/output.zigsrc/bun.js/test/Execution.zigsrc/cli/test_command.zigsrc/bun.js/test/jest.zig
**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/javascriptcore-class.mdc)
**/*.zig: Declare the extern C symbol in Zig and export a Zig-friendly alias for use
Wrap the Bun____toJS extern in a Zig method that takes a JSGlobalObject and returns JSC.JSValue
**/*.zig: Format Zig files with zig-format (bun run zig-format)
In Zig, manage memory carefully with allocators and use defer for cleanup
Files:
src/output.zigsrc/bun.js/test/Execution.zigsrc/cli/test_command.zigsrc/bun.js/test/jest.zig
test/**
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place all tests under the test/ directory
Files:
test/js/bun/test/dots.test.ts
test/js/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place JavaScript and TypeScript tests under test/js/
Files:
test/js/bun/test/dots.test.ts
test/js/bun/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
Place Bun API tests under test/js/bun/, separated by category (e.g., test/js/bun/glob/)
Files:
test/js/bun/test/dots.test.ts
test/**/*.{js,ts}
📄 CodeRabbit inference engine (.cursor/rules/writing-tests.mdc)
test/**/*.{js,ts}: Write tests in JavaScript or TypeScript using Bun’s Jest-style APIs (test, describe, expect) and run with bun test
Prefer data-driven tests (e.g., test.each) to reduce boilerplate
Use shared utilities from test/harness.ts where applicable
Files:
test/js/bun/test/dots.test.ts
test/**/*.test.ts
📄 CodeRabbit inference engine (test/CLAUDE.md)
test/**/*.test.ts: Name test files*.test.tsand usebun:test
Do not write flaky tests: never wait for arbitrary time; wait for conditions instead
Never hardcode port numbers in tests; useport: 0to get a random port
When spawning Bun in tests, usebunExe()andbunEnvfromharness
Preferasync/awaitin tests; for a single callback, usePromise.withResolvers()
Do not set explicit test timeouts; rely on Bun’s built-in timeouts
UsetempDir/tempDirWithFilesfromharnessfor temporary files and directories in tests
For large/repetitive strings in tests, preferBuffer.alloc(count, fill).toString()over"A".repeat(count)
Import common test utilities fromharness(e.g.,bunExe,bunEnv,tempDirWithFiles,tmpdirSync, platform checks, GC helpers)
In error tests, assert non-zero exit codes for failing processes and usetoThrowfor synchronous errors
Usedescribeblocks for grouping,describe.eachfor parameterized tests, snapshots withtoMatchSnapshot, and lifecycle hooks (beforeAll,beforeEach,afterEach); track resources for cleanup inafterEach
Useusing/await usingwith Bun resources (e.g., Bun.listen/connect/spawn/serve) to ensure cleanup in tests
Files:
test/js/bun/test/dots.test.ts
test/js/**
📄 CodeRabbit inference engine (test/CLAUDE.md)
Organize unit tests for specific features under
test/js/by module
Files:
test/js/bun/test/dots.test.ts
test/**/*.test.{ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
test/**/*.test.{ts,tsx}: Test files must be placed under test/ and end with .test.ts or .test.tsx
In tests, always use port: 0; do not hardcode ports or use custom random port functions
In tests, use normalizeBunSnapshot when asserting snapshots
Never write tests that merely assert absence of "panic" or "uncaught exception" in output
Avoid shell commands (e.g., find, grep) in tests; use Bun.Glob and built-ins instead
Prefer snapshot tests over exact stdout equality assertions
Files:
test/js/bun/test/dots.test.ts
**/*.{js,ts,tsx}
📄 CodeRabbit inference engine (CLAUDE.md)
Format JavaScript/TypeScript files with Prettier (bun run prettier)
Files:
test/js/bun/test/dots.test.ts
src/bun.js/**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/zig-javascriptcore-classes.mdc)
src/bun.js/**/*.zig: In Zig binding structs, expose generated bindings via pub const js = JSC.Codegen.JS and re-export toJS/fromJS/fromJSDirect
Constructors and prototype methods should return bun.JSError!JSC.JSValue to integrate Zig error handling with JS exceptions
Use parameter name globalObject (not ctx) and accept (*JSC.JSGlobalObject, *JSC.CallFrame) in binding methods/constructors
Implement getters as get(this, globalObject) returning JSC.JSValue and matching the .classes.ts interface
Provide deinit() for resource cleanup and finalize() that calls deinit(); use bun.destroy(this) or appropriate destroy pattern
Access JS call data via CallFrame (argument(i), argumentCount(), thisValue()) and throw errors with globalObject.throw(...)
For properties marked cache: true, use the generated Zig accessors (NameSetCached/GetCached) to work with GC-owned values
In finalize() for objects holding JS references, release them using .deref() before destroy
Files:
src/bun.js/test/Execution.zigsrc/bun.js/test/jest.zig
🧠 Learnings (14)
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : Name test files `*.test.ts` and use `bun:test`
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/**/*.{js,ts} : Write tests in JavaScript or TypeScript using Bun’s Jest-style APIs (test, describe, expect) and run with bun test
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/js/bun/**/*.{js,ts} : Place Bun API tests under test/js/bun/, separated by category (e.g., test/js/bun/glob/)
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : When spawning Bun in tests, use `bunExe()` and `bunEnv` from `harness`
Applied to files:
test/js/bun/test/dots.test.tssrc/bun.js/test/Execution.zig
📚 Learning: 2025-09-08T04:44:59.101Z
Learnt from: CR
PR: oven-sh/bun#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-08T04:44:59.101Z
Learning: Applies to test/**/*.test.{ts,tsx} : In tests, use normalizeBunSnapshot when asserting snapshots
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:12:56.803Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/writing-tests.mdc:0-0
Timestamp: 2025-08-30T00:12:56.803Z
Learning: Applies to test/cli/**/*.{js,ts} : When testing Bun as a CLI, use spawn with bunExe() and bunEnv from harness, and capture stdout/stderr via pipes
Applied to files:
test/js/bun/test/dots.test.tssrc/bun.js/test/Execution.zig
📚 Learning: 2025-09-03T17:10:13.486Z
Learnt from: CR
PR: oven-sh/bun#0
File: test/CLAUDE.md:0-0
Timestamp: 2025-09-03T17:10:13.486Z
Learning: Applies to test/**/*.test.ts : Import common test utilities from `harness` (e.g., `bunExe`, `bunEnv`, `tempDirWithFiles`, `tmpdirSync`, platform checks, GC helpers)
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-09-20T03:39:41.770Z
Learnt from: pfgithub
PR: oven-sh/bun#22534
File: test/regression/issue/21830.fixture.ts:14-63
Timestamp: 2025-09-20T03:39:41.770Z
Learning: Bun's test runner supports async describe callbacks, unlike Jest/Vitest where describe callbacks must be synchronous. The syntax `describe("name", async () => { ... })` is valid in Bun.
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:09:39.100Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/dev-server-tests.mdc:0-0
Timestamp: 2025-08-30T00:09:39.100Z
Learning: Applies to test/bake/bake-harness.ts : Provide and maintain shared test utilities: devTest, prodTest, devAndProductionTest, Dev, Client, and helpers in the harness
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-09-08T04:44:59.101Z
Learnt from: CR
PR: oven-sh/bun#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-08T04:44:59.101Z
Learning: Applies to test/**/*.test.{ts,tsx} : Avoid shell commands (e.g., find, grep) in tests; use Bun.Glob and built-ins instead
Applied to files:
test/js/bun/test/dots.test.ts
📚 Learning: 2025-08-30T00:13:36.815Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/zig-javascriptcore-classes.mdc:0-0
Timestamp: 2025-08-30T00:13:36.815Z
Learning: Applies to src/bun.js/**/*.zig : Constructors and prototype methods should return bun.JSError!JSC.JSValue to integrate Zig error handling with JS exceptions
Applied to files:
src/bun.js/test/Execution.zig
📚 Learning: 2025-08-30T00:13:36.815Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/zig-javascriptcore-classes.mdc:0-0
Timestamp: 2025-08-30T00:13:36.815Z
Learning: Applies to src/bun.js/**/*.zig : Access JS call data via CallFrame (argument(i), argumentCount(), thisValue()) and throw errors with globalObject.throw(...)
Applied to files:
src/bun.js/test/Execution.zig
📚 Learning: 2025-09-24T05:48:59.872Z
Learnt from: nektro
PR: oven-sh/bun#22806
File: scripts/runner.node.mjs:687-689
Timestamp: 2025-09-24T05:48:59.872Z
Learning: In the Bun codebase, the `startGroup` utility function in scripts/runner.node.mjs automatically closes any previously open group when called, so `startGroup("End")` correctly closes the final test group and keeps subsequent output ungrouped.
Applied to files:
src/bun.js/test/Execution.zig
📚 Learning: 2025-09-08T04:44:59.101Z
Learnt from: CR
PR: oven-sh/bun#0
File: CLAUDE.md:0-0
Timestamp: 2025-09-08T04:44:59.101Z
Learning: Applies to **/*.zig : In Zig, manage memory carefully with allocators and use defer for cleanup
Applied to files:
src/cli/test_command.zig
🧬 Code graph analysis (1)
test/js/bun/test/dots.test.ts (1)
test/harness.ts (2)
bunExe(103-106)normalizeBunSnapshot(1809-1840)
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
- GitHub Check: Format
🔇 Additional comments (14)
src/output.zig (2)
524-536: LGTM! Well-designed RAII-style scope guard.The
EnableBufferingScopestruct correctly implements a scope-based buffering control mechanism that:
- Captures the previous
enable_bufferingstate on initialization- Restores it on deinitialization
- Explicitly documents that
deinit()does not flush (intentional design choice appropriate for test reporters)The implementation is thread-safe since
enable_bufferingis threadlocal (line 429).
538-540: LGTM! Clean factory function for scope guard.The
enableBufferingScope()function provides a clean public API for scoped buffering control. This complements the existingenableBuffering()function (line 520) by offering automatic state restoration via RAII.Typical usage pattern:
const scope = Output.enableBufferingScope(); defer scope.deinit(); // ... buffered operations ... // state automatically restored on scope exitsrc/cli/test_command.zig (5)
579-588: LGTM! Clean structure for the new reporters.The addition of
last_printed_dotfor state tracking and the nestedreportersstruct groupingdotsandjunitflags is a clear improvement over the previous singlefile_reporterfield. The default values are appropriate.
1342-1347: LGTM! Reporter initialization is clean.The initialization correctly checks the test options and sets up the reporters. The dots reporter is just a boolean flag with no memory allocation, while the JUnit reporter is properly instantiated (though needs the destroy fix noted in the previous comment).
1633-1677: Smart indentation for dots mode summary.The
DotIndenterstruct and its usage elegantly handle the formatting difference between dots mode (where a newline separates dots from summary) and normal mode (where a space prefixes summary lines).The logic is correct:
- When in dots mode AND the last output was a dot: skip indent space, print newline (lines 1644-1646)
- Otherwise: indent with space
This ensures the summary always has proper spacing regardless of what was printed before it.
One minor suggestion for clarity:
- const indenter = DotIndenter{ .indent = !(ctx.test_options.reporters.dots and reporter.last_printed_dot) }; + const should_prepend_newline = ctx.test_options.reporters.dots and reporter.last_printed_dot; + const indenter = DotIndenter{ .indent = !should_prepend_newline };This makes the condition more readable.
1740-1745: Final JUnit write is correct, but relies on the destroy fix.The final JUnit reporter cleanup correctly:
- Closes any open test suite
- Writes the report to the configured output file
However, note that this block doesn't destroy the JUnit reporter allocation. That's expected to happen in the defer block at lines 1311-1313 (which needs the
destroy()fix noted earlier).The separation of concerns is appropriate:
- Lines 1740-1745: Normal completion path - write the report
- Lines 1311-1313: Cleanup path (both success and error) - destroy the reporter
Just ensure the destroy fix is applied to prevent the memory leak.
845-892: last_printed_dot behavior for skipped_by_label is correct. The code bypasses dot printing and state updates for.skipped_because_label, solast_printed_dotremains accurate and no extra newline issues occur.src/bun.js/test/Execution.zig (1)
596-596: LGTM! Correctly passes BunTest context to printIfNeeded.The updated call to
runner.current_file.printIfNeeded(this.bunTest())correctly provides the BunTest context, which is needed for the new reporter-driven newline logic in dots mode. This aligns with the signature change insrc/bun.js/test/jest.zigwhereprintIfNeedednow accepts abun_test_parameter.test/js/bun/test/dots.test.ts (1)
1-42: Well-structured dots reporter test.The test correctly:
- Spawns a Bun test process with
--dotsflag and a name filter- Captures stdout/stderr via pipes (as per test guidelines)
- Uses
bunExe(),bunEnv, andnormalizeBunSnapshot()from harness- Asserts the full output including exit code, dots, and summary stats
The snapshot expectations appear reasonable:
- Line 23:
....................shows 20 dots for passing/skipped tests- Lines 24-30: Three failing test messages (expected for
.failing()tests that passed)- Lines 32-36: Summary stats (10 pass, 10 skip, 10 todo, 3 fail across 33 tests)
Minor observation: The filter
-t "filterin"on line 6 appears to be matching test names containing "filterin" (likely "filtering" or similar). Ensure thedots.fixture.tsfile contains tests with this substring to validate the filter is working as intended.src/bun.js/test/jest.zig (5)
10-30: LGTM! Updated set signature for reporter context.The updated
CurrentFile.setfunction now accepts areporter: *CommandLineReporterparameter (line 16), which is needed to checklast_printed_dotstate for newline decisions. The call toshouldPrependExtraNewline(reporter)at line 29 correctly determines whether an extra newline is needed before printing the filename.The logic is sound:
- If AI agent mode: store title/prefix for later printing (lines 18-26)
- Otherwise: print immediately with reporter-aware newline handling (lines 28-29)
69-80: LGTM! Updated printIfNeeded signature.The updated
printIfNeededfunction now acceptsbun_test_: *const bun_test.BunTest(line 69), which allows it to access the reporter for state-aware newline decisions. The logic correctly:
- Returns early if filename already printed (line 70)
- Sets the flag (line 71)
- Calls
The conditional at line 78 correctly handles both cases:
- If reporter exists: call
shouldPrependExtraNewline(reporter)- Otherwise: use
false(no extra newline)
489-496: LGTM! Updated JUnit line number capture.The change from checking
runner.test_options.file_reporter == .junittorunner.test_options.reporters.junit(line 491) correctly aligns with the new nested reporters structure. The logic is unchanged: line numbers are only captured when JUnit reporting is enabled.
529-529: LGTM! Added CommandLineReporter import.The new import of
CommandLineReporterfrom../../cli/test_command.zigis necessary for the type annotations in the updatedCurrentFilefunctions. This creates a dependency fromjest.zigtotest_command.zig, which is appropriate given thatjest.zigneeds to interact with the command-line reporter for dots mode functionality.
37-67: Clarify header newline and simplify flag reset in shouldPrependExtraNewline
- Optional refactor for
shouldPrependExtraNewline:fn shouldPrependExtraNewline(reporter: *CommandLineReporter) bool { - if (reporter.last_printed_dot) { - reporter.last_printed_dot = false; - return true; - } - return false; + const result = reporter.last_printed_dot; + reporter.last_printed_dot = false; + return result; }
- Confirm whether the unconditional
Output.prettyError("<r>\n")is intentional. Please share sample output (first ~20 lines) for:
• Normal mode:bun test /tmp/test_format.test.ts
• Dots mode:bun test /tmp/test_format.test.ts --dots
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
src/bun.js/test/bun_test.zig (1)
717-723: Consider removing redundant flush.The flush at line 721 appears redundant since line 731 already flushes output after error handling completes. You can remove the
bun.Output.flush()call at line 721 to avoid the unnecessary double flush.Apply this diff:
} else if (this.reporter) |reporter| { if (reporter.last_printed_dot and reporter.reporters.dots) { bun.Output.prettyError("<r>\n", .{}); reporter.last_printed_dot = false; - bun.Output.flush(); } }
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
Disabled knowledge base sources:
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (1)
src/bun.js/test/bun_test.zig(1 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
src/**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/building-bun.mdc)
Implement debug logs in Zig using
const log = bun.Output.scoped(.${SCOPE}, false);and invokinglog("...", .{})
Files:
src/bun.js/test/bun_test.zig
**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/javascriptcore-class.mdc)
**/*.zig: Declare the extern C symbol in Zig and export a Zig-friendly alias for use
Wrap the Bun____toJS extern in a Zig method that takes a JSGlobalObject and returns JSC.JSValue
**/*.zig: Format Zig files with zig-format (bun run zig-format)
In Zig, manage memory carefully with allocators and use defer for cleanup
Files:
src/bun.js/test/bun_test.zig
src/bun.js/**/*.zig
📄 CodeRabbit inference engine (.cursor/rules/zig-javascriptcore-classes.mdc)
src/bun.js/**/*.zig: In Zig binding structs, expose generated bindings via pub const js = JSC.Codegen.JS and re-export toJS/fromJS/fromJSDirect
Constructors and prototype methods should return bun.JSError!JSC.JSValue to integrate Zig error handling with JS exceptions
Use parameter name globalObject (not ctx) and accept (*JSC.JSGlobalObject, *JSC.CallFrame) in binding methods/constructors
Implement getters as get(this, globalObject) returning JSC.JSValue and matching the .classes.ts interface
Provide deinit() for resource cleanup and finalize() that calls deinit(); use bun.destroy(this) or appropriate destroy pattern
Access JS call data via CallFrame (argument(i), argumentCount(), thisValue()) and throw errors with globalObject.throw(...)
For properties marked cache: true, use the generated Zig accessors (NameSetCached/GetCached) to work with GC-owned values
In finalize() for objects holding JS references, release them using .deref() before destroy
Files:
src/bun.js/test/bun_test.zig
🧠 Learnings (1)
📚 Learning: 2025-08-30T00:13:36.815Z
Learnt from: CR
PR: oven-sh/bun#0
File: .cursor/rules/zig-javascriptcore-classes.mdc:0-0
Timestamp: 2025-08-30T00:13:36.815Z
Learning: Applies to src/bun.js/**/*.zig : Constructors and prototype methods should return bun.JSError!JSC.JSValue to integrate Zig error handling with JS exceptions
Applied to files:
src/bun.js/test/bun_test.zig
Adds a simple dots reporter for bun test