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

test(evals): record multiple-handoffs' broader prompt match in its oracle version

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
DottaandClaude Opus 5.5 committed 2026-11-08 06:48:02 -06:00
1 parent 6febd9682a
commit ee14526892
2 files changed
+2 -2
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
@@ -320,7 +320,7 @@
"registered-artifact.ts",
"chat-scenarios/agent-chat.yaml"
],
"oracleVersion": "paperclip.chat-catalog.runtime-multiple-handoffs.v3",
"oracleVersion": "paperclip.chat-catalog.runtime-multiple-handoffs.v4",
"coverageGaps": [],
"expectedRunCount": 5,
"setupHumanMessageCount": 1,
tests/runner-e2e/chat-catalog-domains/runtime-multiple-handoffs.ts
+1 -1
View File
@@ -61,7 +61,7 @@ export const runtimeMultipleHandoffCases = [runtimeDefinition("agent-chat.multip
sourceHistoryBound: comments.filter(row => !row.authorAgentId).length === 1 && comments.some(row => !row.authorAgentId
&& row.body?.includes(busy.task.identifier ?? busy.task.id) && row.body.includes(logo.identifier ?? logo.id) && row.body.includes(artifact.attachmentId)), setupRunIds: saved.runs.map(row => row.id) };
}, gradeMultipleHandoffs, {
setupHumanMessageCount: 1, expectedHumanMessageCount: 2, expectedRunCount: 5, attemptTimeoutMs: 1_020_000, oracleVersion: "paperclip.chat-catalog.runtime-multiple-handoffs.v3",
setupHumanMessageCount: 1, expectedHumanMessageCount: 2, expectedRunCount: 5, attemptTimeoutMs: 1_020_000, oracleVersion: "paperclip.chat-catalog.runtime-multiple-handoffs.v4",
sourceFiles: ["chat-catalog-domains/runtime-multiple-handoffs.ts", "chat-catalog-domains/runtime-queue.ts", "chat-catalog-domains/runtime-busy-worker.ts", "chat-catalog-domains/runtime-support.ts", "chat-catalog-domains/identity-support.ts", "registered-artifact.ts", "chat-scenarios/agent-chat.yaml"],
setupPolicy: runtimeQueueCases[0]!.setupPolicy, verifySetup: runtimeQueueCases[0]!.verifySetup,
async act(ctx, state) {