fix(qa): accept Codex capped read evidence

vincentkoc · vincentkoc · commit ee421ef7da7e · 2026-06-24T18:07:40.000+08:00
diff --git a/qa/scenarios/runtime/long-context-cache-stability.yaml b/qa/scenarios/runtime/long-context-cache-stability.yaml
@@ -85,7 +85,7 @@ flow:
           value:
             expr: "env.mock ? [...(await fetchJson(`${env.mock.baseUrl}/debug/requests`))] : []"
         - assert:
-            expr: "!env.mock || debugRequests.some((request) => request.plannedToolName === 'read' && request.plannedToolArgs?.path === config.fixtureFile && String(request.allInputText ?? '').includes(config.cacheEvidenceNeedle) && String(request.allInputText ?? '').includes('[Read output capped at 50KB') && String(request.allInputText ?? '').length >= 50000)"
+            expr: "!env.mock || debugRequests.some((request, index) => request.plannedToolName === 'read' && request.plannedToolArgs?.path === config.fixtureFile && typeof request.plannedToolCallId === 'string' && debugRequests.slice(index + 1).some((result, resultOffset) => result.toolOutputCallId === request.plannedToolCallId && String(result.toolOutput ?? '').includes(config.cacheEvidenceNeedle) && (String(result.toolOutput ?? '').includes('[Read output capped at 50KB') || (String(result.toolOutput ?? '').includes('...(truncated)...') && String(result.toolOutput ?? '').length <= 13000)) && debugRequests.slice(index + resultOffset + 2).some((followup) => followup.plannedToolName === 'read' && followup.plannedToolArgs?.path === config.fixtureFile && String(followup.allInputText ?? '').includes(config.cacheEvidenceNeedle) && (String(followup.allInputText ?? '').includes('[Read output capped at 50KB') || String(followup.allInputText ?? '').includes('...(truncated)...')))))"
             message:
-              expr: "`large capped read tool result was not observed: ${JSON.stringify(debugRequests.slice(-8).map((request) => ({ plannedToolName: request.plannedToolName ?? null, plannedToolArgs: request.plannedToolArgs ?? null, allInputLength: String(request.allInputText ?? '').length, hasNeedle: String(request.allInputText ?? '').includes(config.cacheEvidenceNeedle), hasReadCap: String(request.allInputText ?? '').includes('[Read output capped at 50KB') })))}`"
+              expr: "`large capped read tool result was not observed: ${JSON.stringify(debugRequests.slice(-8).map((request) => ({ plannedToolName: request.plannedToolName ?? null, plannedToolArgs: request.plannedToolArgs ?? null, plannedToolCallId: request.plannedToolCallId ?? null, toolOutputCallId: request.toolOutputCallId ?? null, toolOutputLength: String(request.toolOutput ?? '').length, toolOutputHasNeedle: String(request.toolOutput ?? '').includes(config.cacheEvidenceNeedle), toolOutputHasReadCap: String(request.toolOutput ?? '').includes('[Read output capped at 50KB'), toolOutputHasCodexTruncation: String(request.toolOutput ?? '').includes('...(truncated)...'), inputHasNeedle: String(request.allInputText ?? '').includes(config.cacheEvidenceNeedle), inputHasReadCap: String(request.allInputText ?? '').includes('[Read output capped at 50KB'), inputHasCodexTruncation: String(request.allInputText ?? '').includes('...(truncated)...') })))}`"
       detailsExpr: "outbound?.text ?? config.hitMarker"
