Add to container MCP response

Returned by: Add to container MCP tool
Response type: Structured status snapshot

Response Shape

The tool returns a text message plus the same status details as structured content.

Field	Type	Notes
`status`	string	Operation status. Values are `in_progress`, `completed`, or `failed`.
`message`	string	Human-readable status message for the current snapshot.
`container_id`	string	GovTribe container owner identifier for the operation.
`oai_container_id`	string	Hosted OpenAI container identifier when one exists.
`requested_file_count`	integer	Number of files requested for the container operation.
`completed_file_count`	integer	Number of requested files already attached.
`pending_file_count`	integer	Number of requested files still being attached.
`failed_file_count`	integer	Number of requested files that failed attachment.
`completed_file_names`	string array	File names already available in the hosted container.
`pending_file_names`	string array	File names still being uploaded or attached.
`failed_file_names`	string array	File names that failed attachment.
`skipped_file_names`	string array	File names skipped by the tool before upload.
`hosted_tool_ready`	boolean	Whether the hosted `shell` tool can use the completed files now.
`retry_with_same_arguments`	boolean	Whether the agent should call the same tool again later with identical arguments.
`next_actions`	object array	Structured guidance for the next MCP call or hosted shell workflow step. Each item includes `action`, `tool`, and `reason`.
`failure_reasons`	object array	Detectable failure or skipped-file reasons with `code`, `message`, and `retry_hint`. Empty when no repair guidance is needed.
`container_files`	object array	Completed file references for hosted shell use. Each item includes `name`, `oai_file_id`, `path_hint`, and `sandbox_uri_hint` when available.

Follow-up Behavior

When status is in_progress and retry_with_same_arguments is true, follow next_actions and call Add_To_Container again later with the same arguments to get a fresh status snapshot.

Do not use hosted shell files while status is in_progress or hosted_tool_ready is false.

When status is completed and hosted_tool_ready is true, follow next_actions and use the container_files values in hosted shell workflows. Use path_hint for shell commands and sandbox_uri_hint when a response needs a sandbox link.

When status is failed, inspect failure_reasons before retrying. The response can distinguish no supported files, unsupported file types, and upload or container attachment failure when that information is available.

Example

{
  "status": "completed",
  "message": "Container CONTAINER_ID has 2 requested supported file(s): 2 completed, 0 pending, 0 failed. Completed files: \"pricing-summary.pdf\", \"requirements.xlsx\". Requested files are ready for hosted shell access under /mnt/data.",
  "container_id": "CONTAINER_ID",
  "oai_container_id": "OAI_CONTAINER_ID",
  "requested_file_count": 2,
  "completed_file_count": 2,
  "pending_file_count": 0,
  "failed_file_count": 0,
  "completed_file_names": ["pricing-summary.pdf", "requirements.xlsx"],
  "pending_file_names": [],
  "failed_file_names": [],
  "skipped_file_names": [],
  "hosted_tool_ready": true,
  "retry_with_same_arguments": false,
  "next_actions": [
    {
      "action": "use_hosted_shell",
      "tool": null,
      "reason": "The requested files are ready for hosted shell access. Use container_files path_hint or sandbox_uri_hint values."
    }
  ],
  "failure_reasons": [],
  "container_files": [
    {
      "name": "pricing-summary.pdf",
      "oai_file_id": "file_...",
      "path_hint": "/mnt/data/pricing-summary.pdf",
      "sandbox_uri_hint": "sandbox:/mnt/data/pricing-summary.pdf"
    },
    {
      "name": "requirements.xlsx",
      "oai_file_id": "file_...",
      "path_hint": "/mnt/data/requirements.xlsx",
      "sandbox_uri_hint": "sandbox:/mnt/data/requirements.xlsx"
    }
  ]
}

Response Shape

Follow-up Behavior

Example

On this page