# Steer a run

Sends the user's new message to a run that is still working, so the agent reads it at its next step instead of after the run ends. Use it for a correction or an addition while the agent works; once a run has ended, send the next message with Start a run. Answers `202` with the run: the message is in `steers` as `pending`, and the `run.steered` event marks where the agent read it. If the run is waiting on an approval or a questionnaire, the message declines or skips it and the run continues with the message; it never approves anything. A run that ended or is finishing answers `409 run_not_active` and the message is dropped: send it with Start a run instead. Send an `Idempotency-Key` header to make a retry safe.

`POST /v1/users/{userId}/runs/{runId}/steer`

## Authentication

Both headers are required.

- Header: `X-Api-Key: YOUR_API_KEY`
- Header: `Authorization: Bearer YOUR_USER_TOKEN` — A user's session token, from Create a session.

## Path parameters



```json
[
  {
    "schema": {
      "type": "string",
      "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$"
    },
    "in": "path",
    "name": "userId",
    "required": true,
    "description": "Your id for the user: the `userId` you sent to Create a user. It must be the session's user."
  },
  {
    "schema": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "in": "path",
    "name": "runId",
    "required": true,
    "description": "The run's id."
  }
]
```


## Header parameters



```json
[
  {
    "schema": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "example": "d5565100-9342-4bc6-a803-b387a20cb536",
    "in": "header",
    "name": "idempotency-key",
    "required": false,
    "description": "Optional. A UUID you generate for this request. Send the same key and the same body to retry it safely: you get the original result back, never a second one. Without it, a retry creates a second one."
  }
]
```


## Request body



```json
{
  "required": true,
  "content": {
    "application/json": {
      "schema": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string",
            "minLength": 1,
            "maxLength": 32768,
            "description": "The user's new message for the working agent, up to 32768 characters."
          }
        },
        "required": [
          "text"
        ],
        "additionalProperties": false
      },
      "example": {
        "text": "Use 50 USDC instead of 100."
      }
    }
  }
}
```


## Request example

Illustrative request. Replace the host, credentials and resource IDs with your own. If a request file is shown, create it from the schema above. Review the requested action before sending it.

```sh
curl --request POST 'https://api.example.test/v1/users/YOUR_USER_ID/runs/YOUR_RUN_ID/steer' \
  --header 'X-Api-Key: YOUR_API_KEY' \
  --header 'Authorization: Bearer YOUR_USER_TOKEN' \
  --header 'Content-Type: application/json' \
  --data '{
  "text": "Use 50 USDC instead of 100."
}'
```

## Responses

### 202

The run, with the message in its `steers`; the same run again when this `Idempotency-Key` already sent it.



```json
{
  "description": "The run, with the message in its `steers`; the same run again when this `Idempotency-Key` already sent it.",
  "content": {
    "application/json": {
      "schema": {
        "$ref": "#/components/schemas/Run"
      }
    }
  }
}
```


### 400

The request could not be read as this operation expects.

- `invalid_input` — the body or query failed validation; `issues` names each field
- `invalid_cursor` — the `cursor` is not one this list minted



```json
{
  "description": "The request could not be read as this operation expects.\n\n- `invalid_input` — the body or query failed validation; `issues` names each field\n- `invalid_cursor` — the `cursor` is not one this list minted",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 401

A credential is missing, invalid or expired.

- `partner_key_required` — no `X-Api-Key` header was sent
- `partner_key_invalid` — the `X-Api-Key` is unknown or revoked
- `credential_expired` — the user token has expired; obtain a fresh one



```json
{
  "description": "A credential is missing, invalid or expired.\n\n- `partner_key_required` — no `X-Api-Key` header was sent\n- `partner_key_invalid` — the `X-Api-Key` is unknown or revoked\n- `credential_expired` — the user token has expired; obtain a fresh one",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 403

The credentials are valid but may not do this.

- `subject_mismatch` — the `{userId}` in the path is not the token's user
- `account_disabled` — an operator disabled the account
- `origin_rejected` — a browser `Origin` other than the configured web origin
- `permission_required` — the verified credential is not permitted to make this call
- `steering_disabled` — steering a working run is not turned on for this user; send the message with Start a run once the run ends



```json
{
  "description": "The credentials are valid but may not do this.\n\n- `subject_mismatch` — the `{userId}` in the path is not the token's user\n- `account_disabled` — an operator disabled the account\n- `origin_rejected` — a browser `Origin` other than the configured web origin\n- `permission_required` — the verified credential is not permitted to make this call\n- `steering_disabled` — steering a working run is not turned on for this user; send the message with Start a run once the run ends",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 404

The resource is missing, belongs to someone else, or its id is malformed: all three answer alike.



```json
{
  "description": "The resource is missing, belongs to someone else, or its id is malformed: all three answer alike.",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 409

The operation lost to the current state.

- `run_not_active` — the run named in the path is not the conversation's live run
- `request_key_conflict` — the request identity already binds different terms; retrieve the original resource or use a new identity for a new request



```json
{
  "description": "The operation lost to the current state.\n\n- `run_not_active` — the run named in the path is not the conversation's live run\n- `request_key_conflict` — the request identity already binds different terms; retrieve the original resource or use a new identity for a new request",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 413

The body exceeds the size this deployment accepts.



```json
{
  "description": "The body exceeds the size this deployment accepts.",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 429

A limit refused the request; wait for `Retry-After` when it is sent.

- `rate_limited` — the per-key or per-user limit is spent; honour `Retry-After`
- `partner_request_capacity` — this partner's request quota across all keys and replicas is spent; honour Retry-After
- `execution_capacity` — no capacity is free to run this right now; honour `Retry-After`
- `partner_run_capacity` — this partner's active run quota is full; honour Retry-After and reuse the same request identity



```json
{
  "description": "A limit refused the request; wait for `Retry-After` when it is sent.\n\n- `rate_limited` — the per-key or per-user limit is spent; honour `Retry-After`\n- `partner_request_capacity` — this partner's request quota across all keys and replicas is spent; honour Retry-After\n- `execution_capacity` — no capacity is free to run this right now; honour `Retry-After`\n- `partner_run_capacity` — this partner's active run quota is full; honour Retry-After and reuse the same request identity",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 500

A fault on our side; quote `requestId` when reporting it.

- `internal` — a fault on our side; quote `requestId` when reporting it



```json
{
  "description": "A fault on our side; quote `requestId` when reporting it.\n\n- `internal` — a fault on our side; quote `requestId` when reporting it",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


### 503

The service cannot take this right now (draining, a dependency did not answer, or an operator paused the work); `retryable` says whether to try again.

- `internal` — a fault on our side; quote `requestId` when reporting it
- `execution_unavailable` — the service that runs the agent could not take the work; `retryable` says whether to try again
- `deployment_paused` — an operator paused this kind of work for the deployment; try again later



```json
{
  "description": "The service cannot take this right now (draining, a dependency did not answer, or an operator paused the work); `retryable` says whether to try again.\n\n- `internal` — a fault on our side; quote `requestId` when reporting it\n- `execution_unavailable` — the service that runs the agent could not take the work; `retryable` says whether to try again\n- `deployment_paused` — an operator paused this kind of work for the deployment; try again later",
  "content": {
    "application/problem+json": {
      "schema": {
        "$ref": "#/components/schemas/ProblemDetails"
      }
    }
  }
}
```


## Complete OpenAPI definition

The exact operation and all referenced components, including recursive schemas.



```json
{
  "operation": {
    "operationId": "runs.steer",
    "summary": "Steer a run",
    "tags": [
      "runs"
    ],
    "description": "Sends the user's new message to a run that is still working, so the agent reads it at its next step instead of after the run ends. Use it for a correction or an addition while the agent works; once a run has ended, send the next message with Start a run. Answers `202` with the run: the message is in `steers` as `pending`, and the `run.steered` event marks where the agent read it. If the run is waiting on an approval or a questionnaire, the message declines or skips it and the run continues with the message; it never approves anything. A run that ended or is finishing answers `409 run_not_active` and the message is dropped: send it with Start a run instead. Send an `Idempotency-Key` header to make a retry safe.",
    "requestBody": {
      "required": true,
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "properties": {
              "text": {
                "type": "string",
                "minLength": 1,
                "maxLength": 32768,
                "description": "The user's new message for the working agent, up to 32768 characters."
              }
            },
            "required": [
              "text"
            ],
            "additionalProperties": false
          },
          "example": {
            "text": "Use 50 USDC instead of 100."
          }
        }
      }
    },
    "parameters": [
      {
        "schema": {
          "type": "string",
          "pattern": "^[A-Za-z0-9][A-Za-z0-9._:-]{0,127}$"
        },
        "in": "path",
        "name": "userId",
        "required": true,
        "description": "Your id for the user: the `userId` you sent to Create a user. It must be the session's user."
      },
      {
        "schema": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        },
        "in": "path",
        "name": "runId",
        "required": true,
        "description": "The run's id."
      },
      {
        "schema": {
          "type": "string",
          "format": "uuid",
          "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
        },
        "example": "d5565100-9342-4bc6-a803-b387a20cb536",
        "in": "header",
        "name": "idempotency-key",
        "required": false,
        "description": "Optional. A UUID you generate for this request. Send the same key and the same body to retry it safely: you get the original result back, never a second one. Without it, a retry creates a second one."
      }
    ],
    "security": [
      {
        "apiKey": [],
        "userToken": []
      }
    ],
    "responses": {
      "202": {
        "description": "The run, with the message in its `steers`; the same run again when this `Idempotency-Key` already sent it.",
        "content": {
          "application/json": {
            "schema": {
              "$ref": "#/components/schemas/Run"
            }
          }
        }
      },
      "400": {
        "$ref": "#/components/responses/InvalidInput"
      },
      "401": {
        "$ref": "#/components/responses/Unauthorized"
      },
      "403": {
        "description": "The credentials are valid but may not do this.\n\n- `subject_mismatch` — the `{userId}` in the path is not the token's user\n- `account_disabled` — an operator disabled the account\n- `origin_rejected` — a browser `Origin` other than the configured web origin\n- `permission_required` — the verified credential is not permitted to make this call\n- `steering_disabled` — steering a working run is not turned on for this user; send the message with Start a run once the run ends",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      },
      "404": {
        "$ref": "#/components/responses/NotFound"
      },
      "409": {
        "description": "The operation lost to the current state.\n\n- `run_not_active` — the run named in the path is not the conversation's live run\n- `request_key_conflict` — the request identity already binds different terms; retrieve the original resource or use a new identity for a new request",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      },
      "413": {
        "$ref": "#/components/responses/PayloadTooLarge"
      },
      "429": {
        "description": "A limit refused the request; wait for `Retry-After` when it is sent.\n\n- `rate_limited` — the per-key or per-user limit is spent; honour `Retry-After`\n- `partner_request_capacity` — this partner's request quota across all keys and replicas is spent; honour Retry-After\n- `execution_capacity` — no capacity is free to run this right now; honour `Retry-After`\n- `partner_run_capacity` — this partner's active run quota is full; honour Retry-After and reuse the same request identity",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      },
      "500": {
        "$ref": "#/components/responses/Internal"
      },
      "503": {
        "description": "The service cannot take this right now (draining, a dependency did not answer, or an operator paused the work); `retryable` says whether to try again.\n\n- `internal` — a fault on our side; quote `requestId` when reporting it\n- `execution_unavailable` — the service that runs the agent could not take the work; `retryable` says whether to try again\n- `deployment_paused` — an operator paused this kind of work for the deployment; try again later",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "Run": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "format": "uuid",
            "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
            "description": "The run's id. It stays the same while the run pauses for approvals and resumes."
          },
          "conversationId": {
            "type": "string",
            "format": "uuid",
            "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
            "description": "The conversation's id."
          },
          "input": {
            "description": "The user's message that started the run; null only for old runs that did not keep it.",
            "type": [
              "string",
              "null"
            ]
          },
          "profile": {
            "type": "object",
            "properties": {
              "tools": {
                "description": "The only tools this run may reach. Absent means every registered tool.",
                "maxItems": 64,
                "type": "array",
                "items": {
                  "type": "string",
                  "pattern": "^[a-z][a-z0-9_]{0,63}$",
                  "description": "A tool's name: lowercase, starting with a letter, letters, digits and underscores only."
                }
              },
              "outputContract": {
                "type": "object",
                "properties": {
                  "name": {
                    "type": "string",
                    "pattern": "^[a-z][a-z0-9_]{0,63}$",
                    "description": "A tool's name: lowercase, starting with a letter, letters, digits and underscores only."
                  },
                  "description": {
                    "description": "Meaning of this terminal output contract.",
                    "type": "string",
                    "maxLength": 4096
                  },
                  "schema": {
                    "description": "The immutable strict object schema that the terminal output must satisfy.",
                    "$ref": "#/components/schemas/RunOutputObjectSchema"
                  }
                },
                "required": [
                  "name",
                  "schema"
                ],
                "description": "The immutable admitted output contract, readable without invoking its admission transform."
              },
              "modelId": {
                "description": "The reviewed provider model pinned by trusted admission; absent for historical default selection.",
                "type": "string",
                "minLength": 1,
                "maxLength": 200
              }
            },
            "description": "The tools, output contract and model the run started with. They never change."
          },
          "startedAt": {
            "type": "string",
            "format": "date-time",
            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$",
            "description": "When the run started."
          },
          "endedAt": {
            "anyOf": [
              {
                "type": "string",
                "format": "date-time",
                "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
              },
              {
                "type": "null"
              }
            ],
            "description": "When the run ended; null while it is running or paused for human input or approval."
          },
          "status": {
            "$ref": "#/components/schemas/RunStatus"
          },
          "output": {
            "anyOf": [
              {
                "type": "object",
                "propertyNames": {
                  "type": "string"
                },
                "additionalProperties": {
                  "$ref": "#/components/schemas/JsonValue"
                }
              },
              {
                "type": "null"
              }
            ],
            "description": "The run's terminal structured result, once it has one under its `outputContract`; null otherwise."
          },
          "response": {
            "anyOf": [
              {
                "type": "object",
                "properties": {
                  "text": {
                    "type": "string",
                    "description": "The agent's full reply, never shortened."
                  },
                  "eventSeq": {
                    "type": "integer",
                    "exclusiveMinimum": 0,
                    "maximum": 9007199254740991,
                    "description": "The `seq` of the event that carries the reply."
                  },
                  "completeness": {
                    "type": "string",
                    "enum": [
                      "complete",
                      "partial"
                    ],
                    "description": "`complete` when the run completed; `partial` when it was stopped or failed before finishing."
                  }
                },
                "required": [
                  "text",
                  "eventSeq",
                  "completeness"
                ]
              },
              {
                "type": "null"
              }
            ],
            "description": "The agent's reply since the run last started, resumed or was steered, once it has one."
          },
          "error": {
            "description": "Why the run failed or was stopped; null when neither happened.",
            "type": [
              "string",
              "null"
            ]
          },
          "failure": {
            "anyOf": [
              {
                "type": "object",
                "properties": {
                  "code": {
                    "type": "string",
                    "enum": [
                      "model_timeout",
                      "model_invalid_output",
                      "execution_deadline",
                      "provider_rate_limit",
                      "provider_unavailable",
                      "provider_authentication",
                      "internal_error",
                      "context_too_large",
                      "daily_budget_exhausted",
                      "monthly_budget_exhausted",
                      "budget_frozen",
                      "partner_daily_budget_exhausted",
                      "partner_monthly_budget_exhausted",
                      "unknown"
                    ],
                    "description": "Why the execution failed: `model_timeout` (the model was too slow to respond), `execution_deadline` (the run's active time limit elapsed before it finished), `provider_rate_limit` or `provider_unavailable` (classified from HTTP status or a connection/body-read failure observed by the host), `model_invalid_output` (terminal structured output still failed its required format after bounded repair), `context_too_large` (the request stayed over the model's context window after the host condensed earlier history and retried once), `daily_budget_exhausted`, `monthly_budget_exhausted` or `budget_frozen` (the user's AI budget for the UTC day or month, or an operator's freeze on it, left no room for the run's next model request), `partner_daily_budget_exhausted` or `partner_monthly_budget_exhausted` (the partner account's AI spend limit for the UTC day or month left no room for it), `internal_error` (a host-side fault), or `unknown` when nothing more specific was classified. A budget or spend-limit code means a limit stopped the run, not that the model failed; trying again fails the same way until the limit clears. A raised user budget or a lifted freeze applies at once; a raised partner limit applies from the next UTC day or month, because the open period keeps the cap it started with."
                  },
                  "stage": {
                    "type": "string",
                    "enum": [
                      "model_request",
                      "tool_execution",
                      "finalization"
                    ],
                    "description": "Which phase of the run was executing when it failed: `model_request` while calling or awaiting the model provider, `tool_execution` while running or resuming a tool call, or `finalization` while settling the run's output and accounting after the model finished."
                  },
                  "providerMessage": {
                    "description": "The model provider's own error text, when one was available: credential values are redacted and it is cut to 256 characters, but it is not a content classifier, so other sensitive detail may remain. Treat it as diagnostic context only — never branch on it, and review before showing it to an end user.",
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 256
                  },
                  "diagnosticReference": {
                    "type": "string",
                    "format": "uuid",
                    "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
                    "description": "This failed run's own id, repeated here as one field to cite when asking support to check the host's internal logs for this execution; it carries no meaning beyond that."
                  },
                  "effectWarning": {
                    "type": "string",
                    "const": "Earlier actions may have completed. Partial output does not prove success or a delivery failure. Check receipts before retrying; retrying may repeat actions.",
                    "description": "This build's fixed caution: earlier actions may already have run, so partial output alone never proves success, a delivery failure, or that retrying is free of duplicate effects."
                  }
                },
                "required": [
                  "code",
                  "stage",
                  "diagnosticReference",
                  "effectWarning"
                ]
              },
              {
                "type": "null"
              }
            ],
            "description": "Details of a failure, when recorded."
          },
          "pendingApprovals": {
            "type": "array",
            "items": {
              "type": "string",
              "format": "uuid",
              "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
              "description": "The approval's id."
            },
            "description": "The approvals this run is waiting on, oldest first."
          },
          "pendingQuestions": {
            "type": "array",
            "items": {
              "type": "string",
              "format": "uuid",
              "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
            },
            "description": "The questionnaire ids this run is waiting on, oldest first."
          },
          "steers": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/RunSteer"
            },
            "description": "The messages the user sent this run while it worked, with Steer a run, oldest first; empty when they sent none."
          },
          "feedback": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/RunFeedback"
              },
              {
                "type": "null"
              }
            ],
            "description": "The user's feedback on this run's reply; null until they send it."
          },
          "origin": {
            "anyOf": [
              {
                "type": "object",
                "properties": {
                  "automationId": {
                    "type": "string",
                    "format": "uuid",
                    "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
                    "description": "The automation's id."
                  },
                  "automationRunId": {
                    "type": "string",
                    "format": "uuid",
                    "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
                    "description": "The automation run it carried out: its `id` in List an automation's runs."
                  },
                  "name": {
                    "type": "string",
                    "description": "The automation's name when that automation run was recorded."
                  }
                },
                "required": [
                  "automationId",
                  "automationRunId",
                  "name"
                ]
              },
              {
                "type": "null"
              }
            ],
            "description": "The automation that started this run; `null` for a run the user started with a message."
          },
          "reads": {
            "maxItems": 2,
            "type": "array",
            "items": {
              "type": "string",
              "enum": [
                "account",
                "prices"
              ]
            },
            "description": "What the agent read while it worked, told by the tools whose calls completed: `account` (the user's own balances, holdings, orders or positions) and `prices` (market prices). Empty when it read neither."
          }
        },
        "required": [
          "id",
          "conversationId",
          "input",
          "profile",
          "startedAt",
          "endedAt",
          "status",
          "output",
          "response",
          "error",
          "failure",
          "pendingApprovals",
          "pendingQuestions",
          "steers",
          "feedback",
          "origin",
          "reads"
        ],
        "description": "The agent's work on one message: its status, the agent's reply once it finishes, any approvals or questionnaires it is waiting on, the messages the user sent it while it worked, and the user's feedback on the reply."
      },
      "RunOutputObjectSchema": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "const": "object",
            "description": "JSON Schema type keyword: object."
          },
          "description": {
            "description": "Human-readable meaning of this schema node.",
            "type": "string"
          },
          "properties": {
            "type": "object",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "$ref": "#/components/schemas/RunOutputSchemaNode"
            },
            "description": "Named fields and their strict schemas."
          },
          "required": {
            "type": "array",
            "items": {
              "type": "string"
            },
            "description": "Every declared property is required exactly once."
          },
          "additionalProperties": {
            "type": "boolean",
            "const": false,
            "description": "Always false; undeclared properties are rejected."
          }
        },
        "required": [
          "type",
          "properties",
          "required",
          "additionalProperties"
        ],
        "description": "A strict object with all declared properties required and no extra properties."
      },
      "RunOutputSchemaNode": {
        "description": "A bounded node in the strict JSON Schema supported for run output.",
        "$ref": "#/components/schemas/schema0"
      },
      "schema0": {
        "anyOf": [
          {
            "$ref": "#/components/schemas/RunOutputObjectSchema"
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "array",
                "description": "JSON Schema type keyword: array."
              },
              "description": {
                "description": "Human-readable meaning of this schema node.",
                "type": "string"
              },
              "items": {
                "description": "Schema every array entry must satisfy.",
                "$ref": "#/components/schemas/RunOutputSchemaNode"
              },
              "minItems": {
                "description": "Inclusive minimum number of array entries.",
                "type": "number"
              },
              "maxItems": {
                "description": "Inclusive maximum number of array entries.",
                "type": "number"
              }
            },
            "required": [
              "type",
              "items"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "string",
                "description": "JSON Schema type keyword: string."
              },
              "description": {
                "description": "Human-readable meaning of this schema node.",
                "type": "string"
              },
              "enum": {
                "description": "The allowed literal values, when restricted.",
                "type": "array",
                "items": {
                  "type": "string"
                }
              },
              "minLength": {
                "description": "Inclusive minimum string length.",
                "type": "number"
              },
              "maxLength": {
                "description": "Inclusive maximum string length.",
                "type": "number"
              }
            },
            "required": [
              "type"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "number",
                "description": "JSON Schema type keyword: number."
              },
              "description": {
                "description": "Human-readable meaning of this schema node.",
                "type": "string"
              },
              "enum": {
                "description": "The allowed literal values, when restricted.",
                "type": "array",
                "items": {
                  "type": "number"
                }
              },
              "minimum": {
                "description": "Inclusive numeric lower bound.",
                "type": "number"
              },
              "maximum": {
                "description": "Inclusive numeric upper bound.",
                "type": "number"
              }
            },
            "required": [
              "type"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "integer",
                "description": "JSON Schema type keyword: integer."
              },
              "description": {
                "description": "Human-readable meaning of this schema node.",
                "type": "string"
              },
              "enum": {
                "description": "The allowed literal values, when restricted.",
                "type": "array",
                "items": {
                  "type": "number"
                }
              },
              "minimum": {
                "description": "Inclusive numeric lower bound.",
                "type": "number"
              },
              "maximum": {
                "description": "Inclusive numeric upper bound.",
                "type": "number"
              }
            },
            "required": [
              "type"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "boolean",
                "description": "JSON Schema type keyword: boolean."
              },
              "description": {
                "description": "Human-readable meaning of this schema node.",
                "type": "string"
              },
              "enum": {
                "description": "The allowed literal values, when restricted.",
                "type": "array",
                "items": {
                  "type": "boolean"
                }
              }
            },
            "required": [
              "type"
            ]
          },
          {
            "type": "object",
            "properties": {
              "type": {
                "type": "string",
                "const": "null",
                "description": "JSON Schema type keyword: null."
              },
              "description": {
                "description": "Human-readable meaning of this schema node.",
                "type": "string"
              }
            },
            "required": [
              "type"
            ]
          }
        ],
        "description": "One supported strict JSON Schema node: object, array, string, number, integer, boolean or null."
      },
      "RunStatus": {
        "type": "string",
        "enum": [
          "running",
          "completed",
          "aborted",
          "failed",
          "paused"
        ],
        "description": "What the run is doing: `running`, or how it stopped — `completed` or `failed` once the model finished, `aborted` when stopped early, or `paused` while an approval is pending."
      },
      "JsonValue": {
        "description": "Any JSON value: a string, number, boolean, null, array or object.",
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "number"
          },
          {
            "type": "boolean"
          },
          {
            "type": "null"
          },
          {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/JsonValue"
            }
          },
          {
            "type": "object",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "$ref": "#/components/schemas/JsonValue"
            }
          }
        ]
      },
      "RunSteer": {
        "type": "object",
        "properties": {
          "id": {
            "type": "string",
            "format": "uuid",
            "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
            "description": "The message's id; the `run.steered` event that delivers it names it."
          },
          "text": {
            "type": "string",
            "description": "The message, as the user sent it."
          },
          "status": {
            "type": "string",
            "enum": [
              "pending",
              "delivered",
              "dropped"
            ],
            "description": "`pending` until the agent reads it at its next step; `delivered` once it has; `dropped` when the run ended before the agent read it, so it was never acted on. Send a dropped message again with Start a run."
          },
          "sentAt": {
            "type": "string",
            "format": "date-time",
            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$",
            "description": "When the user sent it."
          },
          "deliveredAt": {
            "anyOf": [
              {
                "type": "string",
                "format": "date-time",
                "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$"
              },
              {
                "type": "null"
              }
            ],
            "description": "When the agent read it; null until it is `delivered`."
          }
        },
        "required": [
          "id",
          "text",
          "status",
          "sentAt",
          "deliveredAt"
        ],
        "description": "A message the user sent a run while it was working, and whether the agent read it."
      },
      "RunFeedback": {
        "type": "object",
        "properties": {
          "rating": {
            "$ref": "#/components/schemas/RunFeedbackRating"
          },
          "reason": {
            "anyOf": [
              {
                "$ref": "#/components/schemas/RunFeedbackReason"
              },
              {
                "type": "null"
              }
            ],
            "description": "Why the user rated it down; null when they gave no reason or rated it `up`."
          },
          "createdAt": {
            "type": "string",
            "format": "date-time",
            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$",
            "description": "When the user first sent feedback on this run's reply."
          },
          "updatedAt": {
            "type": "string",
            "format": "date-time",
            "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$",
            "description": "When the feedback last changed; the same as `createdAt` until it does."
          }
        },
        "required": [
          "rating",
          "reason",
          "createdAt",
          "updatedAt"
        ],
        "description": "The user's feedback on one run's reply: a thumbs-up or thumbs-down, and why."
      },
      "RunFeedbackRating": {
        "type": "string",
        "enum": [
          "up",
          "down"
        ],
        "description": "How the user rated the reply: `up` for a thumbs-up, `down` for a thumbs-down."
      },
      "RunFeedbackReason": {
        "type": "string",
        "enum": [
          "wrong",
          "unhelpful",
          "slow",
          "unsafe",
          "other"
        ],
        "description": "Why the user rated the reply down: `wrong` it was incorrect, `unhelpful` it did not do what was asked, `slow` it took too long, `unsafe` it was risky or inappropriate, `other` none of these."
      },
      "ProblemDetails": {
        "type": "object",
        "properties": {
          "type": {
            "type": "string",
            "description": "The kind of problem as a URN, `urn:fin:error:<kind>`; stable, compare against it"
          },
          "title": {
            "type": "string",
            "description": "The kind's human title, for logs; never parse it"
          },
          "status": {
            "type": "integer",
            "minimum": 400,
            "maximum": 599,
            "description": "The HTTP status, repeated in the body"
          },
          "reason": {
            "description": "The machine-readable why. One of:\n\n- `run_active` (409) — a run already holds this conversation\n- `budget_exhausted` (429) — the user's AI usage budget, or your partner account's AI spend limit, is used up until the next day or month, or an operator froze it\n- `approval_not_pending` (409) — the approval was already decided or has expired, or its id does not exist or belongs to a different conversation\n- `execution_capacity` (429) — no capacity is free to run this right now; honour `Retry-After`\n- `execution_unavailable` (503) — the service that runs the agent could not take the work; `retryable` says whether to try again\n- `stop_pending` (409) — a stop is already in progress and its cleanup is not yet confirmed\n- `automation_changed` (409) — the automation changed while this request was handled; read it again and retry\n- `automation_held` (409) — an operator holds the automation; it fires again when released\n- `automation_invalid` (409) — the automation's definition cannot run as written\n- `automation_paused` (409) — the automation is paused; resume it first\n- `automation_has_no_webhook` (409) — the automation does not run on incoming events, so it has no webhook\n- `automation_limit` (409) — the user already has as many automations as the deployment allows\n- `profile_unknown_tool` (400) — `profile.tools` names a tool this deployment does not have\n- `deployment_paused` (503) — an operator paused this kind of work for the deployment; try again later\n- `run_not_active` (409) — the run named in the path is not the conversation's live run\n- `withdrawal_changed` (409) — the request key already binds different withdrawal terms, or the current balance cannot cover the requested amount\n- `swap_changed` (409) — the swap cannot be made as asked: an asset is no longer available or the current balance cannot cover the amount; get a new quote\n- `order_changed` (409) — the order can no longer be placed as prepared: the agent wallet no longer holds the amount, an asset is no longer offered, or its minimum no longer matches the assets' precision; prepare it again\n- `prediction_order_changed` (409) — the Polymarket order can no longer be placed as signed: the market closed or stopped taking orders, its price is off the market's tick or its size off Polymarket's minimum, its fee or cost would exceed the signed caps, the Polymarket account cannot cover it, or the signature lapsed before it was placed. Nothing was placed; prepare it again\n- `solana_trade_changed` (409) — the Solana trade can no longer run as signed: the token's decimals or program changed, the agent's Solana account or holdings no longer fit it, another Solana trade is running, or the signature lapsed before it started. Nothing moved; prepare it again\n- `trade_not_recoverable` (409) — the original trade or a recovery attempt remains active or uncertain, its unfinished actions lack conclusive recovery proof, or its remaining proposal can no longer be used\n- `order_not_cancelable` (409) — the limit order can no longer be cancelled: it filled or expired, or the swap provider never took it. Read the order for where it stands\n- `grid_not_active` (409) — the grid is not running, so it cannot be paused: it is already paused, stopping or ended. Read the grid for where it stands\n- `grid_not_paused` (409) — the grid is not paused, so there is nothing to resume. Read the grid for where it stands\n- `suggestion_changed` (409) — the suggestion no longer holds: the account or the market moved since fin made it, the user set it aside, or it cannot be made where the user is now. Say it changed, and read the page's suggestions again\n- `request_key_conflict` (409) — the request identity already binds different terms; retrieve the original resource or use a new identity for a new request\n- `question_not_pending` (409) — the questionnaire has already been answered, closed, or is not awaiting this submission\n- `flag_changed` (409) — the flag's targeting changed since you read it; read it again and retry\n- `group_changed` (409) — the group changed or was deleted since you read it; read it again and retry\n- `group_in_use` (409) — a flag's rules still name this group; take it out of those rules first\n- `group_name_taken` (409) — another group already has this name\n- `agent_wallet_required` (409) — create the agent wallet before opening a perps, prediction-market or Solana account\n- `wallet_account_unsupported` (409) — the user's wallet is an Agent API wallet, whose Intents account is a 0x address this route cannot name; read it with Get wallet account, Get wallet account balances and Open a wallet account session instead\n- `conversation_deleted` (410) — the conversation was deleted; its history stays readable\n- `automation_deleted` (410) — the automation was deleted\n- `grid_ended` (410) — the grid stopped, expired or failed; it stays readable but takes no command. A new grid needs the user's approval in chat\n- `credential_expired` (401) — the user token has expired; obtain a fresh one\n- `account_disabled` (403) — an operator disabled the account\n- `perps_disabled` (403) — perps is not enabled for this user\n- `prediction_disabled` (403) — prediction-market trading is not enabled for this user\n- `solana_disabled` (403) — Solana trading is not enabled for this user\n- `no_account` (404) — the user has not opened the account this call reads; open it first\n- `not_available_in_region` (403) — perps funding is unavailable in the user's region for this request; withdrawals remain available\n- `steering_disabled` (403) — steering a working run is not turned on for this user; send the message with Start a run once the run ends\n- `baskets_disabled` (403) — idea baskets are not turned on for this user; hide the Ideas pages and their baskets\n- `basket_buying` (409) — the basket is still buying, so it cannot be deleted yet; try again once its result is in\n- `basket_awaiting_approval` (409) — an approval to buy this basket is still open; decline it in the chat, then delete the basket\n- `basket_step_not_failed` (409) — the step bought, or the basket is not partly bought, so no order can be linked to it; read the basket again\n- `basket_step_linked` (409) — another order is already linked to this step; a link is permanent, so read the basket again\n- `basket_order_not_linkable` (400) — the order cannot stand in for this step: it is not one of the step's `failures[].linkable` orders, or another basket step already holds it\n- `voice_disabled` (403) — voice input is not turned on for this user; let them type instead\n- `voice_unavailable` (503) — this deployment has no speech model, so it cannot transcribe recordings; let the user type instead\n- `provider_unavailable` (503) — an external provider the call depends on did not answer\n- `quote_refused` (400) — 1Click would not quote this request, usually an amount below what it routes or a pair it does not offer; nothing was reserved. Change the amount or the assets and quote again; for a deposit address, no address was issued, so offer another network\n- `invalid_input` (400) — the body or query failed validation; `issues` names each field\n- `internal` (500) — a fault on our side; quote `requestId` when reporting it\n- `partner_key_required` (401) — no `X-Api-Key` header was sent\n- `partner_key_invalid` (401) — the `X-Api-Key` is unknown or revoked\n- `subject_mismatch` (403) — the `{userId}` in the path is not the token's user\n- `origin_rejected` (403) — a browser `Origin` other than the configured web origin\n- `permission_required` (403) — the verified credential is not permitted to make this call\n- `signature_required` (403) — creating the agent wallet needs the user's signature: send the user's signature of `creation.message` from Get the agent wallet as `authorization`\n- `asset_not_withdrawable` (403) — tokenized stocks cannot be withdrawn; sell them first\n- `asset_not_swappable` (403) — the swap names an asset this user cannot buy or trade with this request: a tokenized stock with no `context.country`, or one where tokenized stocks are not available, or bought while buying them is not enabled for the user; or a yield vault's share token bought while the user's `earn` flag is off\n- `asset_not_tradable` (403) — the order names an asset this user cannot buy or trade with this request: a tokenized stock with no `context.country`, or one where tokenized stocks are not available, or bought while buying them is not enabled for the user; or a yield vault's share token bought while the user's `earn` flag is off\n- `solana_token_not_tradable` (403) — Fin won't trade this token: its mint lets someone freeze, move or charge for holdings or pause transfers, it can't be sold back, Fin couldn't read its mint, it has no reliable price, or it is wrapped SOL. A sale is refused only for what would stop it landing\n- `limit_orders_disabled` (403) — limit orders are not enabled for this user\n- `grid_trading_disabled` (403) — grid trading is not enabled for this user, so a paused grid cannot be resumed; pausing and cancelling a grid are never gated\n- `deposit_limit_exceeded` (429) — the deposit would take the agent wallet past the user's deposit limit, or, for a deposit address, the wallet has no room left under it; nothing was recorded. Read `depositLimit.availableCents` from Get balances for how much fits now, and deposit no more than that\n- `policy_change_throttled` (429) — the user's Agent API wallet changed what it allows a few minutes ago, and the NEAR Intents Agent API lets it change again only after a cooldown; nothing was asked or signed, so call again once `Retry-After` has passed\n- `agent_slippage_exceeded` (403) — the user's wallet is an Agent API wallet whose agent signs only trades that lose at most the share of their value its owner allowed (`max_slippage_bps`): fees, price and slippage together, by 1Click's own USD values at the quote's minimum output. This trade's quote loses more, states no USD value, or, before there is a quote, its loss bound is already quoted with more slippage than that (half the bound, plus 1Click's fee at the most it has been seen to take, 20 basis points, before an approval). Very small trades lose more to fixed fees; nothing was signed, so ask again with a larger amount or a smaller loss bound\n- `agent_api_orders_unavailable` (403) — the user's Agent API wallet needs wallet setup to enable limit orders, or the order exceeds this wallet's 168-hour maximum; finish wallet setup or choose at most 168 hours before trying again; nothing was approved or signed\n- `destination_not_allowed` (403) — the user's wallet is an Agent API wallet, whose agent pays a deposit only to itself, to a NEAR Intents account its owner listed (on the confidential ledger) or to an address on a chain its owner listed; allow this one with Add a withdrawal destination (one owner signature), then ask again. A public NEAR Intents account, or an address with no valid spelling on its chain, cannot be paid at all; nothing was signed\n- `rate_limited` (429) — the per-key or per-user limit is spent; honour `Retry-After`\n- `partner_request_capacity` (429) — this partner's request quota across all keys and replicas is spent; honour Retry-After\n- `partner_run_capacity` (429) — this partner's active run quota is full; honour Retry-After and reuse the same request identity\n- `stream_capacity` (429) — the partner, user or replica has no free stream capacity; honour `Retry-After`\n- `invalid_cursor` (400) — the `cursor` is not one this list minted\n- `invalid_question_answer` (400) — the questionnaire answer does not match its questions or allowed choices\n- `question_closed` (410) — the questionnaire expired or was cancelled\n- `unknown_target` (400) — a rule names a partner, group or user that does not exist, or a user outside the partners the same rule names\n- `scope_invalid` (400) — a subject in the scope is not a subject id, or appears twice\n- `subject_unsupported` (404) — a subject in the scope is not one market briefs cover; list them with List market subjects\n- `brief_not_found` (404) — no market brief job with this id was created with your partner key\n- `briefs_busy` (429) — your market briefs are at their limit of briefs generating at once; retry after `Retry-After`\n- `market_briefs_disabled` (403) — market briefs are not turned on for your partner key\n- `story_not_found` (404) — no market story with this id is current: it never was one, or Fin no longer shows it because its sources were withdrawn or its figures can no longer be read",
            "type": "string",
            "enum": [
              "run_active",
              "budget_exhausted",
              "approval_not_pending",
              "execution_capacity",
              "execution_unavailable",
              "stop_pending",
              "automation_changed",
              "automation_held",
              "automation_invalid",
              "automation_paused",
              "automation_has_no_webhook",
              "automation_limit",
              "profile_unknown_tool",
              "deployment_paused",
              "run_not_active",
              "withdrawal_changed",
              "swap_changed",
              "order_changed",
              "prediction_order_changed",
              "solana_trade_changed",
              "trade_not_recoverable",
              "order_not_cancelable",
              "grid_not_active",
              "grid_not_paused",
              "suggestion_changed",
              "request_key_conflict",
              "question_not_pending",
              "flag_changed",
              "group_changed",
              "group_in_use",
              "group_name_taken",
              "agent_wallet_required",
              "wallet_account_unsupported",
              "conversation_deleted",
              "automation_deleted",
              "grid_ended",
              "credential_expired",
              "account_disabled",
              "perps_disabled",
              "prediction_disabled",
              "solana_disabled",
              "no_account",
              "not_available_in_region",
              "steering_disabled",
              "baskets_disabled",
              "basket_buying",
              "basket_awaiting_approval",
              "basket_step_not_failed",
              "basket_step_linked",
              "basket_order_not_linkable",
              "voice_disabled",
              "voice_unavailable",
              "provider_unavailable",
              "quote_refused",
              "invalid_input",
              "internal",
              "partner_key_required",
              "partner_key_invalid",
              "subject_mismatch",
              "origin_rejected",
              "permission_required",
              "signature_required",
              "asset_not_withdrawable",
              "asset_not_swappable",
              "asset_not_tradable",
              "solana_token_not_tradable",
              "limit_orders_disabled",
              "grid_trading_disabled",
              "deposit_limit_exceeded",
              "policy_change_throttled",
              "agent_slippage_exceeded",
              "agent_api_orders_unavailable",
              "destination_not_allowed",
              "rate_limited",
              "partner_request_capacity",
              "partner_run_capacity",
              "stream_capacity",
              "invalid_cursor",
              "invalid_question_answer",
              "question_closed",
              "unknown_target",
              "scope_invalid",
              "subject_unsupported",
              "brief_not_found",
              "briefs_busy",
              "market_briefs_disabled",
              "story_not_found"
            ]
          },
          "requestId": {
            "type": "string",
            "description": "The id Fin used for this request; quote it when reporting a problem"
          },
          "retryable": {
            "type": "boolean",
            "description": "Whether repeating the same request later can succeed without changing it"
          },
          "detail": {
            "description": "Only on `invalid_input`: which part of the request failed validation",
            "type": "string"
          },
          "issues": {
            "description": "Only on `invalid_input`: one entry per failing field",
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "path": {
                  "type": "string",
                  "description": "The JSON pointer of the failing field; empty for the root object"
                },
                "message": {
                  "type": "string",
                  "description": "Why the field failed"
                }
              },
              "required": [
                "path",
                "message"
              ]
            }
          }
        },
        "required": [
          "type",
          "title",
          "status",
          "requestId",
          "retryable"
        ],
        "description": "RFC 9457 problem details: what every error response carries. Never a provider's message, a query or a stack."
      }
    },
    "responses": {
      "InvalidInput": {
        "description": "The request could not be read as this operation expects.\n\n- `invalid_input` — the body or query failed validation; `issues` names each field\n- `invalid_cursor` — the `cursor` is not one this list minted",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      },
      "Unauthorized": {
        "description": "A credential is missing, invalid or expired.\n\n- `partner_key_required` — no `X-Api-Key` header was sent\n- `partner_key_invalid` — the `X-Api-Key` is unknown or revoked\n- `credential_expired` — the user token has expired; obtain a fresh one",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      },
      "NotFound": {
        "description": "The resource is missing, belongs to someone else, or its id is malformed: all three answer alike.",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      },
      "PayloadTooLarge": {
        "description": "The body exceeds the size this deployment accepts.",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      },
      "Internal": {
        "description": "A fault on our side; quote `requestId` when reporting it.\n\n- `internal` — a fault on our side; quote `requestId` when reporting it",
        "content": {
          "application/problem+json": {
            "schema": {
              "$ref": "#/components/schemas/ProblemDetails"
            }
          }
        }
      }
    },
    "securitySchemes": {
      "apiKey": {
        "type": "apiKey",
        "in": "header",
        "name": "X-Api-Key"
      },
      "userToken": {
        "type": "http",
        "scheme": "bearer",
        "bearerFormat": "fin_session_<opaque>",
        "description": "A user's session token, from Create a session."
      }
    }
  }
}
```

