Multiple Similar Messages in Single ResponsesAPI Response

Cross-linking — we’re seeing the same duplicate/similar output within a single response on gpt-5.5 (thinking) via the Responses API. A cross-model A/B isolates it to gpt-5.5 (gpt-4.1 0/30, claude-sonnet-4-6 0/30), and token billing confirms the model itself generates the second copy — clean openings bill ~77–93 output tokens, doubled ones ~130–258. Consolidated evidence: Regression: Double responses in apps

Happy to share request IDs / a sanitized payload.