feat(phase9): LlmEngine::extract_content_tags + smoke test

Added as a method on LlmEngine alongside cleanup_text and
extract_tasks; same render_chat_prompt -> generate -> parse pattern.
Truncates the transcript to its trailing 2000 chars on a UTF-8 char
boundary, runs at temperature 0.0 with the CONTENT_TAGS_GRAMMAR GBNF,
and re-validates intent against INTENT_CLOSED_SET to catch the
unlikely grammar bypass case. max_tokens 96 is enough for the JSON
envelope. Smoke test gated on KON_LLM_TEST_MODEL like the existing
smoke.rs.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-04-25 00:02:12 +01:00
parent 1b6ad88ead
commit 7567bede52
2 changed files with 106 additions and 0 deletions

View File

@@ -0,0 +1,48 @@
//! Smoke test for Phase 9 LlmEngine::extract_content_tags.
//!
//! Gated behind the same `KON_LLM_TEST_MODEL` env var as the existing
//! smoke.rs test so neither runs in default `cargo test` runs (model
//! load is heavy). Run explicitly with:
//!
//! KON_LLM_TEST_MODEL=/path/to/model.gguf cargo test -p kon-llm \
//! --test content_tags_smoke -- --nocapture
use std::env;
use std::path::PathBuf;
use kon_llm::{is_valid_intent, LlmEngine, LlmModelId};
#[test]
fn extract_content_tags_returns_valid_pair() {
let model_path = match env::var("KON_LLM_TEST_MODEL") {
Ok(path) => PathBuf::from(path),
Err(_) => {
eprintln!("KON_LLM_TEST_MODEL not set — skipping");
return;
}
};
let engine = LlmEngine::new();
engine
.load_model(LlmModelId::Qwen3_1_7B_Q4, &model_path, true)
.expect("load model");
let transcript = "Tomorrow I need to run through the grant application one more time \
and make sure the figures add up. I also need to book a slot with \
Rachmann for the Mac test and email Andrew about the meeting window.";
let tags = engine
.extract_content_tags(transcript)
.expect("extract_content_tags");
assert!(tags.topic.len() >= 3, "topic present: {tags:?}");
assert!(
tags.topic
.chars()
.all(|c| c.is_ascii_lowercase() || c.is_ascii_digit() || c == '-'),
"topic lowercase + slugged: {tags:?}",
);
assert!(
is_valid_intent(&tags.intent),
"intent in closed set: {tags:?}",
);
}