appgrammar_breed
Axiom: IV — Architecture | Category: Composition
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.
Breed two appgrammars by analyzing module graphs and merging selected modules from each parent.
The breeding process compares module graphs to identify shared modules, unique modules, and conflicts. Conflict types include duplicate (same module in both), dependency (cross-parent dependency), and overlap (same module name but different step counts). The server returns a merge prompt with the analysis; your LLM resolves conflicts and produces integration decisions.
Flow:
- Call
appgrammar_breedwith two parent IDs — creates a breeding session and returns a merge prompt + one-time token (30-minute expiry) - Run the prompt on your LLM to get integration decisions
- Submit the result via
appgrammar_tool_submit— the server validates and assembles the child appgrammar from merged modules
The child appgrammar carries traceable lineage back to both parents.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
source_appgrammar_id_a | string (UUID) | Yes | ID of the first parent appgrammar. |
source_appgrammar_id_b | string (UUID) | Yes | ID of the second parent appgrammar. Must be different from the first. |
params | object | No | Optional tool-specific parameters. |
Example
{
"method": "tools/call",
"params": {
"name": "appgrammar_breed",
"arguments": {
"source_appgrammar_id_a": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
"source_appgrammar_id_b": "f9e8d7c6-b5a4-3210-fedc-ba9876543210"
}
}
}