From 7c455027d96262697fb8acade40fb6bc0a6cb037 Mon Sep 17 00:00:00 2001 From: "Molecule AI Dev Engineer A (Kimi)" Date: Thu, 4 Jun 2026 05:05:29 +0000 Subject: [PATCH 1/2] fix(e2e): increase liveness probe max_tokens from 4 to 32 Reasoning models (MiniMax M2.7, Moonshot K2.6) can spend the entire 4-token budget on reasoning, leaving zero tokens for the actual response. Bump the per-provider liveness probe to 32 so reasoning models have headroom to emit both reasoning and content. Part of issue #2204. Co-Authored-By: Claude Opus 4.7 --- tests/e2e/test_staging_full_saas.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/e2e/test_staging_full_saas.sh b/tests/e2e/test_staging_full_saas.sh index b7d8ea1b7..8aa976e20 100755 --- a/tests/e2e/test_staging_full_saas.sh +++ b/tests/e2e/test_staging_full_saas.sh @@ -1011,7 +1011,7 @@ print(json.dumps({ 'messageId': f'e2e-{uuid.uuid4().hex[:8]}', 'parts': [{'kind': 'text', 'text': 'Reply with exactly: ok'}], }, - 'configuration': {'max_tokens': 4} + 'configuration': {'max_tokens': 32} } })) ") -- 2.52.0 From e9de8af66c8b67c8d3c759034c0c4c60bd5dd9b8 Mon Sep 17 00:00:00 2001 From: "Molecule AI Dev Engineer A (Kimi)" Date: Thu, 4 Jun 2026 05:51:17 +0000 Subject: [PATCH 2/2] chore: retrigger CI after E2E flake -- 2.52.0