Jannik/PaperClipAI
1
0 Fork 0
mirror of https://github.com/paperclipai/paperclip.git synced 2026-11-10 12:37:55 +01:00
Code Issues Packages Projects Releases Wiki Activity

fix(evals): follow a rendered task link in revise-delivery only when one exists

Browse Source 
The revision request attaches its source task, so the shared result-navigation
check's requirement for a rendered task link rejected a correct reply that
returned both version downloads. The case still opens the returned download and
both versions' library stacks.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
DottaandClaude Opus 5.5 committed 2026-11-07 21:11:27 -06:00
1 parent a3f29839fd
commit 470db33754
2 files changed
+6 -3
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

tests/runner-e2e/chat-catalog-descriptors.json
+1 -1
View File
@@ -2872,7 +2872,7 @@
"chat-catalog-domains/internal-website-delivery.ts",
"registered-artifact.ts"
],
"oracleVersion": "paperclip.chat-catalog.internal.website-revision.v2",
"oracleVersion": "paperclip.chat-catalog.internal.website-revision.v3",
"coverageGaps": [],
"expectedRunCount": 2,
"minimumRunCount": 2,
tests/runner-e2e/chat-catalog-domains/internal-website-delivery.ts
+5 -2
View File
@@ -102,7 +102,7 @@ function websiteDelivery(revising: boolean): ChatCatalogCase {
const state = { project: p, task: handedOff, worker, priorRunId, filename, producedBody: actual, producedHash: hash(actual), marker, bodyFact, signupHref, originalAttachment, originalProductId, selectedSource, factualContextAttachment: selectedSource.factualContextAttachment };
await ctx.input.evidence("chat-catalog-actual-prior-website.json", state); return state;
}, gradeWebsiteDelivery);
return { ...base, ...(revising ? { oracleVersion: "paperclip.chat-catalog.internal.website-revision.v2" } : {}), authentication: "human-session", queryAttachments: factualContextQueryAttachment("selected-source.md"), expectedRunCount: 2, minimumRunCount: 2, attemptTimeoutMs: 600_000,
return { ...base, ...(revising ? { oracleVersion: "paperclip.chat-catalog.internal.website-revision.v3" } : {}), authentication: "human-session", queryAttachments: factualContextQueryAttachment("selected-source.md"), expectedRunCount: 2, minimumRunCount: 2, attemptTimeoutMs: 600_000,
sourceFiles: [...base.sourceFiles, "chat-catalog-domains/internal-website-delivery.ts", "registered-artifact.ts"],
async observe(ctx, state): Promise<DeliveryObservation> {
const o = await observeInternal(ctx, state); const ids = [entity(state, "task").id, ...(ctx.issue() ? [ctx.issue()!.id] : [])];
@@ -112,7 +112,10 @@ function websiteDelivery(revising: boolean): ChatCatalogCase {
return { ...o, attachments, products, downloaded, ...(ctx.issue() ? { chatIssueId: ctx.issue()!.id } : {}) };
},
async verifyResult(ctx, state, value) {
const o = value as DeliveryObservation; await base.verifyResult(ctx, state, value);
const o = value as DeliveryObservation;
// The revision request already attaches the source task; follow a rendered task link when one exists,
// while the returned download and both library stacks below are always opened.
if (!revising || o.tasks.some(row => hasLink(o, "issues", row))) await base.verifyResult(ctx, state, value);
const file = deliveredFiles(o).find(row => downloadHref(o, row)); if (!file) throw new Error("Missing exact registered download result");
const href = downloadHref(o, file)!; const page = await ctx.input.page.context().newPage();
try {