Agent Schedules6

Agents11

Alerts7

Annotation Queues10

API keys6

Audio3

Budgets6

Chat1

Chunking1

Classify1

Completions1

Datasets13

Deployments4

Embeddings1

Environments5

Evals9

Feedback4

File Systems10

Files6

Guardrail Rules6

Hub2

Human Review Sets5

Identities5

Images3

Knowledge Bases23

Logs10

Management keys6

MCP Gateway13

Memory Stores15

Model Catalog3

Model Fusions6

Models17

Moderations1

Notifiers5

Policies5

Projects5

Prompts7

Reporting1

Rerank1

Responses3

Router1

Routing Rules6

Skills5

Smart Routers5

Telemetry3

Threads7

Tools7

Traces10

Webhooks8

Workspace Security8

Workspace Settings2

Workspaces3

Responses

Compact response

Compacts a conversation by summarizing older items to free up context window space. Returns a compaction item containing the generated summary.

post/v1/responses/compact

Request body

instructionsstring

Custom instructions for the compaction summarization.

modelstring

The model to use for compaction in provider/model format (e.g. openai/gpt-4o). Required.

previous_response_idstring

The ID of a previous response to continue from.

prompt_cache_keystring

Key for prompt caching across requests.

Response

Compaction completed successfully.

created_atinteger required

Unix timestamp (seconds) when the response was created.

idstring required

The ID of the compaction response.

object'response.compaction' required

Always "response.compaction".

Changes

Changed in 1 of the 350 revisions of this API.1

Sep 28, 20263c7d859558ee1See the full diff
- ○
  endpoint added
  endpoint-added
This revision also has 27 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

Of the 350 revisions, 136 have no diff computed.

Full history