Fix OpenAI Responses API tool-call 400s, wrong call_id errors, truncated JSON, and invalid_json_schema failures in Python and TypeScript.

Fix OpenAI Assistants API sunset migration failures by converting Threads and Runs to Conversations and Responses without losing history, images, or tool calls.

Learn how startups use GPT-5.6 to build faster, more cost-efficient AI agents with smarter model selection and new Responses API capabilities.

OpenAI has enhanced its Responses API with new tools like image generation, Code Interpreter, and MCP server support, empowering developers to build more sophisticated and action-oriented AI agents for...

SentinelLABS evaluated OpenAI's native Responses API compaction for long-running malware analysis workflows and found it cut input tokens by about 86% with no measurable change in overall evaluation score. The study concluded that compaction can reduce noise and cost while preserving task quality, though it may slightly weaken domain object modeling in some cases. #OpenAI #ResponsesAPI #SentinelLABS

All impacted services have now fully recovered.

Agents are talked about everywhere. Agentic is the new 2025 buzzword. OpenAI is going heads on against Anthropic when it comes to…

OpenAIのエージェント構築用API「Responses API」がMCPに対応し他のツールとの連携が容易に&Responses APIで画像生成機能も利用可能に #ResponsesAPI #ウェブ検索 #ファイル検索 #コンピューターの操作 #ModelContextProtocol #ITニュース

OpenAI、新API「Responses API」発表 – AIエージェント開発のハードルを下げる新ツール #ResponsesAPI #AgentsSDK #ITニュース

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.

Hi, there. I have been using gpt-4.1 model for ResponsesAPI to implement web search with OpenAI and it has been working properly. Once GPT-5.2 model is launched, I have upgraded the model to GPT-5.2. But it seems like it’s not enabled to do web search. When asking “Can you do web search“ for GPT-4.1 model, it worked great but for GPT-5.2, it’s not working. Also, my agent is asking any additional data source instead of doing web search internally. I hope you please help me to fix this. Thank you.

There is a bug in ResponsesApi. I don’t send top_p in payload, but error is the result.

I’m experiencing the exact same issue on my client implementation. With the ResponsesAPI, file citations only map back to the file level, not the specific chunk returned by the `file_search` tool. In the AssistantsAPI, we were able to link citations directly to the chunk used in the answer, which is essential for our UX. Is there currently any way to retrieve or correlate the chunk associated with a given annotation? Or is this functionality no longer supported in the new API?

We are in the process of migrating our application from using AssistantsAPI to ResponsesAPI. When using the file_seach tool with ResponsesAPI, the relevant output looks like the following: { “type”: “response.output_item.done”, “sequence_number”: 8, “output_index”: 1, “item”: { “id”: “fs_id”, “type”: “file_search_call”, “status”: “completed”, “queries”: [ “query1”, “query2”, ], “results”: [ { “attributes”: {}, “file_id”: “file_id”, “filename”: “filename.pdf”, “score”: 0.6731, “text”: “chunk text”, “vector_store_id”: “vs_id” }, { “type”: “response.output_text.annotation.added”, “sequence_number”: 656, “item_id”: “item_id”, “output_index”: 3, “content_index”: 0, “annotation_index”: 18, “annotation”: { “type”: “file_citation”, “file_id”: “file_id”, “filename”: “filename.pdf”, “index”: 3320 } } “type”: “response.content_part.done”, “sequence_number”: 711, “item_id”: “item_id”, “output_index”: 3, “content_index”: 0, “part”: { “type”: “output_text”, “annotations”: [ { “type”: “file_citation”, “file_id”: “file_id”, “filename”: “filename.pdf”, “index”: 438 },] This does not allow tying back an annotation to a specific chunk, only to a specific file. We’d like to expose to our users the specific chunk that was used to answer the question, not just the file. In AssistantsAPI this is a functionality we had, and we’d like to keep it the same. Is there a configuration setting or something else we’re missing or is this simply not possible with ResponsesAPI?

Hey @jasondouglas , we’ve also been experiencing this issue. Almost 1 out of every 20 of our responses in the last 48 hours have had duplicate/similar output text within the same response. Could we be opted in to the fix as well? happy to followup wherever is appropriate with details Thanks!