spec 5 linked patterns checked
OpenAI Responses streaming events reference
Documents streamed response event types emitted when a Response is created with stream enabled.
Read with a purpose
What this source can teach
Use this source to check a technical or accessibility requirement against its exact wording and scope.
- Start with the original. Open the source and find the guidance or example relevant to your task.
- Trace the connection. Use the claim notes below to see how this site applies the source to specific patterns.
- Check the setting. Compare the source's platform, people, and constraints with your own decision.
Pattern Decisions This Source Supports
| Pattern | Supported decision | Required contract | Claim note |
|---|---|---|---|
| Agent plan preview | Choose agent plan preview when an AI agent's proposed multi-step execution needs review before it starts. | The preview names the objective, plan version, source context, model or workflow instructions, planned tools, and expected output before run. | Supports separating pre-run plan preview from later streamed response and tool events. |
| Agent progress trace | Choose agent progress trace when an agent or automation run has started and users need live status across multiple steps or tools. | The trace belongs to one run ID, reviewed plan version, objective, actor, start time, current state, and final state. | Supports event-based updates that can map to live response, tool, and run milestones. |
| Regenerate / retry | Choose regenerate / retry when the task is rerunning an AI response attempt, creating a new answer version, continuing a failed generation, or recovering from failed AI source or tool work. | Retry same prompt repeats the submitted prompt and visible context unless the UI explicitly shows which context changed. | Supports event-based handling for partial, failed, and completed generated responses. |
| Streaming response | Choose streaming response when partial generated output is useful before the full answer is ready and the product can explain partial versus final state. | The UI never presents an active stream as a complete answer until the terminal event or final validation state arrives. | Supports event-specific lifecycle handling for streamed responses. |
| Tool-use visibility | Choose tool-use visibility when users need to inspect exact tool names, purposes, inputs, outputs, permissions, side effects, failures, or redactions. | Each tool-use item identifies one tool call or tool-call attempt with stable call ID, run ID, step ID, tool name, status, timestamp, and permission scope. | Supports event-based lifecycle handling while tool-related work proceeds. |
Comparisons supported by this source
- Agent plan preview vs task list vs recommended next action vs human approval gate vs step navigation
Supports separating previewed plans from later response and tool execution events.
- Agent progress trace vs agent plan preview vs streaming response vs activity log vs progress bar vs human approval gate
Supports event-based live updates for response and tool execution surfaces.
- Regenerate / retry vs retry vs chat interface vs streaming response vs prompt box vs editable AI output
Supports partial, failed, and completed response lifecycle handling.
- Streaming response vs chat interface vs progress bar vs loading spinner vs feed
Supports event-specific handling for streamed response lifecycle states.
- Tool-use visibility vs agent progress trace vs source grounding display vs citation display vs activity log vs human approval gate
Supports event-based lifecycle handling during tool and response work.
Evidence Role
This source is treated as spec evidence. Its value comes from the specific claims and setting described above.
Publisher: OpenAI. Last checked: .