appgrammar_update
Axiom: VII — Algebra | Category: Feedback Loop
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.
Update an existing appgrammar to reflect codebase changes. Returns the current appgrammar state for the agent to diff against. Submit structured changes (added/removed/updated modules).
After an appgrammar is executed and the application is built, the developer continues iterating — adding features, fixing bugs, refactoring modules. Over time, the appgrammar drifts from reality. The update tool closes the feedback loop: the agent compares the current codebase against the blueprint, identifies structural changes, and submits a structured changeset (modules added, removed, or updated). If the caller owns the appgrammar, the update is applied in place with an automatic version snapshot. Otherwise, a fork is created.
This is a multi-turn operation. The first call returns the full appgrammar state (modules, instructions, config). The agent analyzes the codebase, then submits changes via appgrammar_tool_submit.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
source_appgrammar_id | string (UUID) | Yes | ID of the appgrammar to update. |
mode | "version" | "copy" | No | Mode: "version" updates in place (owner only, auto-falls back to copy for non-owners), "copy" creates a new child. Defaults to "version". |
params | object | No | Optional tool-specific parameters. |
Example
{
"method": "tools/call",
"params": {
"name": "appgrammar_update",
"arguments": {
"source_appgrammar_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
}
}
}