取消运行

Cancels a run that is `in_progress`.

post

https://api.portkey.ai/v1SELF_HOSTED_GATEWAY_URL

/threads/{thread_id}/runs/{run_id}/cancel

Authorizations

Portkey-Key & Virtual-KeyPortkey-Key & Provider-Auth & Provider-NameConfig & Portkey-KeyCustom-Host & Portkey-Key & Provider-Auth & Provider-Name

x-portkey-api-keystringRequired

x-portkey-virtual-keystringRequired

Path parameters

thread_idstringRequired

The ID of the thread to which this run belongs.

run_idstringRequired

The ID of the run to cancel.

Responses

200

OK

application/json

Represents an execution run on a thread.

idstringRequired

The identifier, which can be referenced in API endpoints.

objectstring · enumRequired

The object type, which is always thread.run.

Possible values:

created_atintegerRequired

The Unix timestamp (in seconds) for when the run was created.

thread_idstringRequired

The ID of the thread that was executed on as a part of this run.

assistant_idstringRequired

The ID of the assistant used for execution of this run.

statusstring · enumRequired

The status of the run, which can be either queued, in_progress, requires_action, cancelling, cancelled, failed, completed, incomplete, or expired.

Possible values:

expires_atinteger · nullableRequired

The Unix timestamp (in seconds) for when the run will expire.

started_atinteger · nullableRequired

The Unix timestamp (in seconds) for when the run was started.

cancelled_atinteger · nullableRequired

The Unix timestamp (in seconds) for when the run was cancelled.

failed_atinteger · nullableRequired

The Unix timestamp (in seconds) for when the run failed.

completed_atinteger · nullableRequired

The Unix timestamp (in seconds) for when the run was completed.

modelstringRequired

The model that the assistant used for this run.

instructionsstringRequired

The instructions that the assistant used for this run.

metadataobject · nullableRequired

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format. Keys can be a maximum of 64 characters long and values can be a maxium of 512 characters long.

temperaturenumber · nullableOptional

The sampling temperature used for this run. If not set, defaults to 1.

top_pnumber · nullableOptional

The nucleus sampling value used for this run. If not set, defaults to 1.

max_prompt_tokensinteger · min: 256 · nullableRequired

The maximum number of prompt tokens specified to have been used over the course of the run.

max_completion_tokensinteger · min: 256 · nullableRequired

The maximum number of completion tokens specified to have been used over the course of the run.

tool_choiceone of · nullableRequired

Controls which (if any) tool is called by the model. none means the model will not call any tools and instead generates a message. auto is the default value and means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user. Specifying a particular tool like {"type": "file_search"} or {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

string · enumOptional

none means the model will not call any tools and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools before responding to the user.

Possible values:

or

parallel_tool_callsbooleanRequired

Whether to enable parallel function calling during tool use.

Default: true

response_formatone of · nullableRequired

Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

Setting to { "type": "json_object" } enables JSON mode, which guarantees the message the model generates is valid JSON.

Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

string · enumOptional

auto is the default value

Possible values:

or

post

/threads/{thread_id}/runs/{run_id}/cancel

curlpythonjavascript

curl https://api.portkey.ai/v1/threads/thread_abc123/runs/run_abc123/cancel \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-virtual-key: $PORTKEY_PROVIDER_VIRTUAL_KEY" \
  -H "OpenAI-Beta: assistants=v2" \
  -X POST

200

OK

{
  "id": "text",
  "object": "thread.run",
  "created_at": 1,
  "thread_id": "text",
  "assistant_id": "text",
  "status": "queued",
  "required_action": {
    "type": "submit_tool_outputs",
    "submit_tool_outputs": {
      "tool_calls": [
        {
          "id": "text",
          "type": "function",
          "function": {
            "name": "text",
            "arguments": "text"
          }
        }
      ]
    }
  },
  "last_error": {
    "code": "server_error",
    "message": "text"
  },
  "expires_at": 1,
  "started_at": 1,
  "cancelled_at": 1,
  "failed_at": 1,
  "completed_at": 1,
  "incomplete_details": {
    "reason": "max_completion_tokens"
  },
  "model": "text",
  "instructions": "text",
  "tools": [
    {
      "type": "code_interpreter"
    }
  ],
  "metadata": {},
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 1,
    "total_tokens": 1
  },
  "temperature": 1,
  "top_p": 1,
  "max_prompt_tokens": 1,
  "max_completion_tokens": 1,
  "truncation_strategy": {
    "type": "auto",
    "last_messages": 1
  },
  "tool_choice": "none",
  "parallel_tool_calls": true,
  "response_format": "none"
}