Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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 package.json
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,7 @@
"@types/proper-lockfile": "4.1.4",
"mem0ai": "3.1.1",
"tsup": "^8.0.0",
"typescript": "^5.9.3",
"typescript": "^6.0.3",
"vite": "8.1.5",
"vitest": "^4.1.10"
},
Expand Down
60 changes: 30 additions & 30 deletions pnpm-lock.yaml

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

64 changes: 34 additions & 30 deletions tests/loops/claim-grounding-ab.test.ts
Original file line number Diff line number Diff line change
Expand Up @@ -204,37 +204,41 @@ afterEach(async () => {
describe('claim-grounding A/B (offline, controlled): catches misattribution dedup+relevance miss', () => {
it('only the claim-grounding verifier rejects the planted misattributions', async () => {
let groundPasses = 0
await runTwoAgentResearchLoop({
root: groundRoot,
goal,
worker: poolWorker(() => {
groundPasses += 1
await Promise.all([
runTwoAgentResearchLoop({
root: groundRoot,
goal,
worker: poolWorker(() => {
groundPasses += 1
}),
driver: { verifySource: createClaimGroundingVerifier() },
readinessSpecs: specs,
maxRounds: 1,
}),
driver: { verifySource: createClaimGroundingVerifier() },
readinessSpecs: specs,
maxRounds: 1,
})
await runTwoAgentResearchLoop({
root: relevanceRoot,
goal,
worker: poolWorker(() => {}),
driver: relevanceOnlyDriver,
readinessSpecs: specs,
maxRounds: 1,
})
await runTwoAgentResearchLoop({
root: noneRoot,
goal,
worker: poolWorker(() => {}),
driver: acceptAllDriver,
readinessSpecs: specs,
maxRounds: 1,
})

const groundMis = await misattributedAdmitted(groundRoot)
const relevanceMis = await misattributedAdmitted(relevanceRoot)
const noneMis = await misattributedAdmitted(noneRoot)
const groundAdmitted = await admittedCount(groundRoot)
runTwoAgentResearchLoop({
root: relevanceRoot,
goal,
worker: poolWorker(() => {}),
driver: relevanceOnlyDriver,
readinessSpecs: specs,
maxRounds: 1,
}),
runTwoAgentResearchLoop({
root: noneRoot,
goal,
worker: poolWorker(() => {}),
driver: acceptAllDriver,
readinessSpecs: specs,
maxRounds: 1,
}),
])

const [groundMis, relevanceMis, noneMis, groundAdmitted] = await Promise.all([
misattributedAdmitted(groundRoot),
misattributedAdmitted(relevanceRoot),
misattributedAdmitted(noneRoot),
admittedCount(groundRoot),
])

console.log(
`[claim-grounding A/B offline] misattributed admitted — ` +
Expand Down
3 changes: 2 additions & 1 deletion tsconfig.json
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,8 @@
"noUnusedLocals": true,
"noUnusedParameters": true,
"noFallthroughCasesInSwitch": true,
"noUncheckedIndexedAccess": true
"noUncheckedIndexedAccess": true,
"ignoreDeprecations": "6.0"
},
"include": ["src"],
"exclude": ["node_modules", "dist", "tests"]
Expand Down
Loading