appgrammar_create_submit

Axiom: I — Compression | Category: Creation

Multi-turn operation

This tool uses a multi-turn protocol. The initial call returns a prompt and token. Run the prompt on your LLM, then submit the structured output via appgrammar_tool_submit (or the tool-specific submit variant) to advance the operation.

Submit the result of an appgrammar creation step. After calling appgrammar_create, you receive a prompt to run on your LLM. Submit the LLM's structured output here.

The server validates the result against the expected schema. If valid, it returns the next step's prompt. After all 5 steps complete, the appgrammar is assembled and ready for execution.

Pipeline steps:

1. Architecture extraction
2. Design system extraction
3. Task DAG construction
4. File registry with exact exports
5. Step enrichment with compressed specifications

Returns one of:

• Next step: { step, system_message, prompt, schema, token } — run this prompt next
• Validation error: { error, details, retry_token, retries_remaining } — fix and resubmit
• Complete: { status: "ready", steps, estimated_tokens_saved, price, preview } — appgrammar is ready, use appgrammar_start

Parameters

Parameter	Type	Required	Description
appgrammar_id	string (UUID)	Yes	The appgrammar ID returned by appgrammar_create.
token	string (UUID)	Yes	Single-use token from the previous step response. Tokens expire after 30 minutes.
result	object	Yes	The structured JSON output from running the prompt on your LLM. Must conform to the schema provided in the previous step.

Example

{
  "method": "tools/call",
  "params": {
    "name": "appgrammar_create_submit",
    "arguments": {
      "appgrammar_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
      "token": "11111111-2222-3333-4444-555555555555",
      "result": {
        "...": "structured LLM output"
      }
    }
  }
}