jcoffey-dev
d9a6db025b
A new method, inbuxa:Explanation/set, asks the node's local model for a short plain-words reading of one thing an administrator is looking at: a failed recipient in the queue, a Classify verdict, a log line or trace event, or one setting with its saved value. The server builds the prompt itself from stored data and the registry schema, never from text the console sends, and grounds SMTP replies in RFC 3463 and RFC 5321. What the model is never shown: secrets (including ones nested inside a setting, like an AI model's HTTP auth), raw protocol events, and the contents of any other event. A tag name that doesn't have a tag's shape is refused before a model is asked. Calls share the AI gate with spam classification, but mail always keeps its slot, and Explain has its own hourly count per account and its own on/off switch in inbuxa:AiLimits. The permission is sysAiExplain, superuser only; tenant administrators can't use it. The session carries an aiExplain flag so a console knows when to offer the button. An install whose roles were stored before the permission existed gets it added once, at start-up, to the roles that are administrators' alone, not the User role their defaults share with every account. An operator who removes it later isn't overruled. Tests: unit tests in inbuxa-features and jmap, and ai_explain_tests (run with --ignored) covering the acceptance tests and the upgrade.
19 lines
487 B
Rust
19 lines
487 B
Rust
/*
|
|
* SPDX-FileCopyrightText: 2026 Coffey Labs
|
|
*
|
|
* SPDX-License-Identifier: AGPL-3.0-only
|
|
*/
|
|
|
|
//! AI spam classification and the LLM Sieve function
|
|
//! (`docs/spec/features/ai-spam-classification.md`). Models are the
|
|
//! operator's own, reached over the OpenAI-compatible API; nothing is preset
|
|
//! and nothing is sent until an administrator configures a model (AI-1).
|
|
|
|
pub mod answer;
|
|
pub mod explain;
|
|
pub mod gate;
|
|
pub mod limits;
|
|
pub mod locality;
|
|
pub mod request;
|
|
pub mod writes;
|