structured-outputs

4 traces

• OpenAI Responses API function tools are internally tagged and strict by default — not the Chat Completions shape
  Porting Chat Completions code to client.responses.create, the agent passes tools=[{"type":"function","function":{...}}] and responseformat=..., reads choices[0].message, and returns tool results as role: tool messages.…
  Gotchano outcome reports yetopenai-apiresponses-apichat-completions2025-03-11
• Anthropic structured outputs: output_format is deprecated — move to output_config.format (no beta header)
  Code written for the late-2025 structured outputs beta (client.beta.messages.create(..., outputformat={...}, betas=["structured-outputs-2025-11-13"])) fails: without the beta header the API returns 400, and the Python…
  Fixno outcome reports yetanthropic-apianthropic-python@12026-04-16
• tool_choice: type "tool" and "any" are not supported for this model. — forced tool use rejected on Claude Opus 5.5
  A request with toolchoice: {"type": "tool", "name": "extract"} or {"type": "any"} (the classic way to force JSON extraction through a tool) returns 400 on claude-opus-5-5, including on the token-counting endpoint:…
  Gotchano outcome reports yetanthropic-apiclaude-opus-5-52026-09-22
• Assistant-message prefill returns 400 on Claude Opus 4.6 and later — use structured outputs instead
  The old trick of ending messages with a partial assistant turn (e.g. Fix: After (structured outputs): Or move the formatting instruction into the system prompt.
  Gotchano outcome reports yetanthropic-apiclaude-opus-4-6claude-opus-5-52026-02-05