Skip to content

fix(test): isolate run-loop mocks from run-eval suite #27

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
antongulin merged 1 commit into from
Jun 17, 2026
Merged

fix(test): isolate run-loop mocks from run-eval suite #27

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion plugin/package.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
"scripts": {
"build": "node ./scripts/build.mjs",
"test": "node --test test/*.test.mjs",
"test:ts": "bun test test/*.test.ts",
"test:ts": "bun test --isolate test/*.test.ts",
"prepack": "npm run build && npm test && npm run test:ts"
},
"dependencies": {
Expand Down
105 changes: 51 additions & 54 deletions plugin/test/run-loop.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,7 @@
import { afterEach, expect, mock, test } from "bun:test"
import { expect, mock, test } from "bun:test"

import type { EvalItem, EvalOutput, EvalResultItem } from "../lib/run-eval"

const calls: { evalResults: EvalOutput }[] = []

const result = (
query: string,
overrides: Partial<EvalResultItem> = {},
Expand All @@ -19,59 +17,56 @@ const result = (
...overrides,
})

Comment thread
antongulin marked this conversation as resolved.
mock.module("../lib/utils", () => ({
parseSkillMd: () => ({
name: "warning-skill",
description: "original description",
fullContent: "skill content",
}),
}))
test("runLoop derives train warnings from train results and prints unique split warnings", async () => {
const calls: { evalResults: EvalOutput }[] = []

mock.module("../lib/utils", () => ({
parseSkillMd: () => ({
name: "warning-skill",
description: "original description",
fullContent: "skill content",
}),
}))

mock.module("../lib/run-eval", () => ({
findProjectRoot: () => "/tmp/project",
buildEvalWarnings: (results: EvalResultItem[]) => {
const shouldTriggerResults = results.filter((r) => r.should_trigger)
if (shouldTriggerResults.length === 0) return []
return shouldTriggerResults.every((r) => r.triggers === 0 && r.errors === 0)
? ["all-zero warning"]
: []
},
runEval: () => ({
skill_name: "warning-skill",
description: "original description",
results: [
result("train trigger"),
result("train negative", { should_trigger: false }),
result("test trigger"),
],
warnings: [],
summary: {
passed: 1,
failed: 2,
total: 3,
run_errors: 0,
queries_with_errors: 0,
mock.module("../lib/run-eval", () => ({
findProjectRoot: () => "/tmp/project",
buildEvalWarnings: (results: EvalResultItem[]) => {
const shouldTriggerResults = results.filter((r) => r.should_trigger)
if (shouldTriggerResults.length === 0) return []
return shouldTriggerResults.every((r) => r.triggers === 0 && r.errors === 0)
? ["all-zero warning"]
: []
},
}),
}))
runEval: () => ({
skill_name: "warning-skill",
description: "original description",
results: [
result("train trigger"),
result("train negative", { should_trigger: false }),
result("test trigger"),
],
warnings: [],
summary: {
passed: 1,
failed: 2,
total: 3,
run_errors: 0,
queries_with_errors: 0,
},
}),
}))

mock.module("../lib/improve-description", () => ({
improveDescription: (opts: { evalResults: EvalOutput }) => {
calls.push({ evalResults: opts.evalResults })
return "improved description"
},
}))
mock.module("../lib/improve-description", () => ({
improveDescription: (opts: { evalResults: EvalOutput }) => {
calls.push({ evalResults: opts.evalResults })
return "improved description"
},
}))

mock.module("../lib/report", () => ({
generateHtml: () => "<html></html>",
}))
mock.module("../lib/report", () => ({
generateHtml: () => "<html></html>",
}))

afterEach(() => {
calls.length = 0
})

test("runLoop derives train warnings from train results and prints unique split warnings", async () => {
const { runLoop } = await import("../lib/run-loop")
const evalSet: EvalItem[] = [
{ query: "train trigger", should_trigger: true },
{ query: "train negative", should_trigger: false },
Expand All @@ -84,6 +79,7 @@ test("runLoop derives train warnings from train results and prints unique split
}

try {
const { runLoop } = await import("../lib/run-loop")
await runLoop({
evalSet,
skillPath: "/tmp/skill/SKILL.md",
Expand All @@ -97,10 +93,11 @@ test("runLoop derives train warnings from train results and prints unique split
agent: undefined,
verbose: true,
})

expect(calls[0]?.evalResults.warnings).toEqual(["all-zero warning"])
expect(errors.filter((line) => line === "Warning: all-zero warning")).toHaveLength(2)
} finally {
console.error = originalError
mock.restore()
}

expect(calls[0]?.evalResults.warnings).toEqual(["all-zero warning"])
expect(errors.filter((line) => line === "Warning: all-zero warning")).toHaveLength(2)
})