mirror of
https://github.com/NanmiCoder/cc-haha
synced 2026-07-16 13:03:31 +08:00
f6511ab278
The desktop product needs a repeatable local gate that can prove the core Coding Agent loop still works after changes, not only that unit tests pass. This adds a quality-gate runner with PR, baseline, and release modes, structured reports, explicit quarantine metadata, and fixture-based live baseline cases that can run across provider/model targets. Constraint: Existing check:pr and CI policy behavior must remain usable while the stronger baseline grows around it Constraint: Default PR gates must not require real model credentials or provider quota Rejected: Build a standalone QA platform first | too heavy before the baseline task shape is proven Rejected: Keep unstable server exclusions hardcoded in run-server-tests | hides quarantine policy from reports and future review Confidence: medium Scope-risk: moderate Directive: Expand baseline cases by adding focused fixtures and verifiers; do not make normal PR checks depend on live providers Tested: bun test scripts/quality-gate/*.test.ts scripts/quality-gate/baseline/*.test.ts Tested: bun run check:server Tested: bun run quality:gate --mode baseline --allow-live --provider-model 2944f963-ce75-45b7-bac1-6e4f57df0970:kimi-k2.6:volc-kimi-k2.6 --provider-model 9c78d3df-7fb5-44c7-8436-3a41c3a59231:MiniMax-M2.7-highspeed:minimax-m2.7 Not-tested: desktop UI browser smoke and native release mode in this commit
62 lines
2.1 KiB
TypeScript
62 lines
2.1 KiB
TypeScript
import { baselineCases } from './baseline/cases'
|
|
import type { BaselineTarget, LaneDefinition, QualityGateMode } from './types'
|
|
|
|
export function lanesForMode(mode: QualityGateMode, baselineTargets: BaselineTarget[] = []): LaneDefinition[] {
|
|
const lanes: LaneDefinition[] = [
|
|
{
|
|
id: 'impact-report',
|
|
title: 'Impact report',
|
|
description: 'Summarize changed areas, required local checks, and risk notes.',
|
|
kind: 'command',
|
|
command: ['bun', 'run', 'check:impact'],
|
|
requiredForModes: ['pr', 'baseline', 'release'],
|
|
},
|
|
{
|
|
id: 'pr-checks',
|
|
title: 'Path-aware PR checks',
|
|
description: 'Run the existing local PR gate with stable path-aware checks.',
|
|
kind: 'command',
|
|
command: ['bun', 'run', 'check:pr'],
|
|
requiredForModes: ['pr', 'release'],
|
|
},
|
|
{
|
|
id: 'baseline-catalog',
|
|
title: 'Baseline case catalog validation',
|
|
description: 'Validate real Coding Agent baseline case definitions and fixture metadata.',
|
|
kind: 'command',
|
|
command: ['bun', 'test', 'scripts/quality-gate/baseline/cases.test.ts'],
|
|
requiredForModes: ['baseline', 'release'],
|
|
},
|
|
{
|
|
id: 'native-checks',
|
|
title: 'Native desktop checks',
|
|
description: 'Build sidecars and run the Tauri native compile check.',
|
|
kind: 'command',
|
|
command: ['bun', 'run', 'check:native'],
|
|
requiredForModes: ['release'],
|
|
},
|
|
]
|
|
|
|
const targets = baselineTargets.length > 0
|
|
? baselineTargets
|
|
: [{ providerId: null, modelId: 'current', label: 'current-runtime' }]
|
|
|
|
for (const testCase of baselineCases) {
|
|
for (const target of targets) {
|
|
const targetSlug = target.label.replace(/[^a-zA-Z0-9._-]+/g, '-')
|
|
lanes.push({
|
|
id: `baseline:${testCase.id}:${targetSlug}`,
|
|
title: `${testCase.title} (${target.label})`,
|
|
description: testCase.description,
|
|
kind: 'baseline-case',
|
|
baselineCaseId: testCase.id,
|
|
baselineTarget: target,
|
|
requiredForModes: ['baseline', 'release'],
|
|
live: true,
|
|
})
|
|
}
|
|
}
|
|
|
|
return lanes.filter((lane) => lane.requiredForModes.includes(mode))
|
|
}
|