feat: Corrections tab — SFT candidate import, review, and JSONL export #15

Merged
pyr0ball merged 99 commits from feat/sft-corrections into main 2026-04-08 22:19:01 -07:00
2 changed files with 33 additions and 30 deletions
Showing only changes of commit 137a9dbb8e - Show all commits

View file

@ -3,28 +3,31 @@ import { useSftStore } from './sft'
import type { SftQueueItem } from './sft'
import { beforeEach, describe, it, expect } from 'vitest'
const MOCK_ITEM: SftQueueItem = {
id: 'abc',
source: 'cf-orch-benchmark',
benchmark_run_id: 'run1',
timestamp: '2026-04-07T10:00:00Z',
status: 'needs_review',
prompt_messages: [
{ role: 'system', content: 'You are a coding assistant.' },
{ role: 'user', content: 'Write a Python add function.' },
],
model_response: 'def add(a, b): return a - b',
corrected_response: null,
quality_score: 0.2,
failure_reason: 'pattern_match: 0/2 matched',
task_id: 'code-fn',
task_type: 'code',
task_name: 'Code: Write a Python function',
model_id: 'Qwen/Qwen2.5-3B',
model_name: 'Qwen2.5-3B',
node_id: 'heimdall',
gpu_id: 0,
tokens_per_sec: 38.4,
function makeMockItem(overrides: Partial<SftQueueItem> = {}): SftQueueItem {
return {
id: 'abc',
source: 'cf-orch-benchmark',
benchmark_run_id: 'run1',
timestamp: '2026-04-07T10:00:00Z',
status: 'needs_review',
prompt_messages: [
{ role: 'system', content: 'You are a coding assistant.' },
{ role: 'user', content: 'Write a Python add function.' },
],
model_response: 'def add(a, b): return a - b',
corrected_response: null,
quality_score: 0.2,
failure_reason: 'pattern_match: 0/2 matched',
task_id: 'code-fn',
task_type: 'code',
task_name: 'Code: Write a Python function',
model_id: 'Qwen/Qwen2.5-3B',
model_name: 'Qwen2.5-3B',
node_id: 'heimdall',
gpu_id: 0,
tokens_per_sec: 38.4,
...overrides,
}
}
describe('useSftStore', () => {
@ -38,37 +41,37 @@ describe('useSftStore', () => {
it('current returns first item', () => {
const store = useSftStore()
store.queue = [MOCK_ITEM]
store.queue = [makeMockItem()]
expect(store.current?.id).toBe('abc')
})
it('removeCurrentFromQueue removes first item', () => {
const store = useSftStore()
const second = { ...MOCK_ITEM, id: 'def' }
store.queue = [MOCK_ITEM, second]
const second = makeMockItem({ id: 'def' })
store.queue = [makeMockItem(), second]
store.removeCurrentFromQueue()
expect(store.queue[0].id).toBe('def')
})
it('restoreItem adds to front of queue', () => {
const store = useSftStore()
const second = { ...MOCK_ITEM, id: 'def' }
const second = makeMockItem({ id: 'def' })
store.queue = [second]
store.restoreItem(MOCK_ITEM)
store.restoreItem(makeMockItem())
expect(store.queue[0].id).toBe('abc')
expect(store.queue[1].id).toBe('def')
})
it('setLastAction records the action', () => {
const store = useSftStore()
store.setLastAction('discard', MOCK_ITEM)
store.setLastAction('discard', makeMockItem())
expect(store.lastAction?.type).toBe('discard')
expect(store.lastAction?.item.id).toBe('abc')
})
it('clearLastAction nulls lastAction', () => {
const store = useSftStore()
store.setLastAction('flag', MOCK_ITEM)
store.setLastAction('flag', makeMockItem())
store.clearLastAction()
expect(store.lastAction).toBeNull()
})

View file

@ -12,7 +12,7 @@ export interface SftQueueItem {
model_response: string
corrected_response: string | null
quality_score: number // 0.0 to 1.0
failure_reason: string
failure_reason: string | null
task_id: string
task_type: string
task_name: string