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): fail retire-agent setup when the historical record starts work

Browse Source 
The baseline and second runs both had a third Morgan run, queued by creating
the done historical task. Assert in setup that Morgan's only run is the
active assignment, so this shows up as a setup defect, not a candidate one.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
DottaandClaude Opus 5.5 committed 2026-11-07 22:32:43 -06:00
1 parent 0656683b5b
commit 031aab4041
2 files changed
+6 -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
+2 -1
View File
@@ -790,7 +790,8 @@
"invariantCheckIds": [
"lead-ready",
"real-active-assignment",
"truthful-historical-work"
"truthful-historical-work",
"historical-record-starts-no-work"
]
},
"runPolicy": {
tests/runner-e2e/chat-catalog-domains/runtime-retirement.ts
+4 -1
View File
@@ -47,7 +47,7 @@ export const runtimeRetirementCases = [runtimeDefinition("agents.retire-agent",
sourceFiles: ["chat-catalog-domains/runtime-retirement.ts", "chat-catalog-domains/runtime-busy-worker.ts", "chat-catalog-domains/runtime-support.ts", "chat-scenarios/agents.yaml"],
expectedRunCount: 2, attemptTimeoutMs: 600_000,
runPolicy: { kind: "terminal-counts", terminalStatusCounts: { succeeded: 1, cancelled: 1 } },
setupPolicy: { readiness: "preserve-scenario", invariantCheckIds: ["lead-ready", "real-active-assignment", "truthful-historical-work"] },
setupPolicy: { readiness: "preserve-scenario", invariantCheckIds: ["lead-ready", "real-active-assignment", "truthful-historical-work", "historical-record-starts-no-work"] },
async verifySetup(ctx, state) {
const c = checks(); const worker = state.worker as RuntimeAgent;
const lead = await ctx.input.api.get<RuntimeAgent>(`/api/agents/${ctx.input.fixtures.agent.id}`);
@@ -61,6 +61,9 @@ export const runtimeRetirementCases = [runtimeDefinition("agents.retire-agent",
c.add("truthful-historical-work", historical.status === "done" && historical.assigneeAgentId === worker.id
&& historical.companyId === ctx.input.fixtures.company.id && !historical.createdByAgentId && !historical.createdByRunId,
"The independently read prior completed record has genuine human provenance, without forged model history.");
const workerRuns = (await ctx.allRuns()).filter(row => row.agentId === worker.id);
c.add("historical-record-starts-no-work", workerRuns.length === 1 && workerRuns[0]?.id === state.workerRunId,
"Recording finished work starts no run: Morgan's only run is the active assignment.");
return c.result();
},
async act(ctx, state) {