boxmaker/crates/memoryd/tests/recall.rs

//! `recall`: quoted terms only, ranked hits with source tags and labels, the result's label, and
//! the recall log (M5a spec, section 5). Do not edit.

#[path = "support/logs.rs"]
mod logs;
#[path = "support/tmp.rs"]
mod tmp;

use bxcore::{DataClass, RecallArgs, Timestamp};
use logs::{assistant, result, user, write_log};
use memoryd::files::Store;
use memoryd::index::Index;
use memoryd::recall::{recall, terms};
use tmp::TempDir;

fn now() -> Timestamp {
    Timestamp::parse("2026-09-24T21:00:00.000Z").unwrap()
}

struct Setup {
    dir: TempDir,
    store: Store,
    index: Index,
}

fn setup(tag: &str) -> Setup {
    let dir = TempDir::new(tag);
    let starter = dir.write("etc/soul.md", "Soul.\n");
    let store = Store::new(&dir.path().join("memory"));
    store.init(&starter).unwrap();
    let index = Index::open(&dir.path().join("index/memory.sqlite3"), DataClass::Private).unwrap();
    Setup { dir, store, index }
}

fn ask(s: &Setup, query: &str, k: u64) -> memoryd::recall::Recalled {
    let args = RecallArgs {
        query: query.to_string(),
        k,
    };
    recall(&s.index, &s.store, &args, "mm-now", now()).unwrap()
}

#[test]
fn terms_are_quoted_and_operators_never_pass() {
    assert_eq!(
        terms("launch window"),
        Some("\"launch\" OR \"window\"".to_string())
    );
    assert_eq!(
        terms(r#"a NEAR(b c) OR "x" title:y z* ^w -v"#),
        Some(
            r#""a" OR "NEAR" OR "b" OR "c" OR "OR" OR "x" OR "title" OR "y" OR "z" OR "w" OR "v""#
                .to_string()
        )
    );
    assert_eq!(terms("Київ 東京"), Some("\"Київ\" OR \"東京\"".to_string()));
    assert_eq!(terms("*** ::: \"\""), None);
}

#[test]
fn hits_are_tagged_and_labelled() {
    let s = setup("recall-tags");
    write_log(
        s.dir.path(),
        "mm-a",
        &[
            user(2, "The launch window moved to Thursday."),
            assistant(
                3,
                None,
                &[("http_fetch", r#"{"url":"https://example.org/launch"}"#)],
            ),
            result(4, "page", DataClass::Private, true),
            assistant(5, Some("The page says the launch is in March."), &[]),
        ],
    );
    s.index
        .catch_up(&s.dir.path().join("sessions"), &s.store.path("notes.md"))
        .unwrap();
    std::fs::write(
        s.store.path("notes.md"),
        "§ moved 2026-09-24T20:14Z from memory.md in session mm-b\nOwner cares about the launch.\n§ dropped 2026-09-24T20:15Z from user.md in session mm-b\nOld launch plan.\n§ noted 2026-09-22T18:20Z in session mm-c · private · untrusted\nexample.org says the launch moved.\n",
    )
    .unwrap();
    s.index
        .catch_up(&s.dir.path().join("sessions"), &s.store.path("notes.md"))
        .unwrap();
    let got = ask(&s, "launch", 10);
    let headers: Vec<&str> = got.text.lines().filter(|l| l.starts_with('[')).collect();
    let mut sorted: Vec<String> = headers
        .iter()
        .map(|h| h.split_once("] ").unwrap().1.to_string())
        .collect();
    sorted.sort();
    assert_eq!(
        sorted,
        [
            "identity · moved 2026-09-24 from memory.md · private",
            "memory · dropped 2026-09-24 from user.md · private",
            "memory · session mm-a, 2026-09-20 14:02 UTC, the owner said · private",
            "memory · session mm-a, 2026-09-20 14:03 UTC, the assistant called · private",
            "memory-tainted · note, 2026-09-22 18:20 UTC, session mm-c · private",
            "memory-tainted · session mm-a, 2026-09-20 14:05 UTC, the assistant said · private",
        ]
    );
    assert!(got.text.starts_with("[1] "));
    assert!(got.text.contains("\nThe launch window moved to Thursday."));
    assert!(!got.text.contains("page\n"), "tool results are not indexed");
    assert_eq!((got.class, got.untrusted), (DataClass::Private, true));
}

#[test]
fn a_clean_result_is_trusted_and_k_limits_the_hits() {
    let s = setup("recall-clean");
    write_log(
        s.dir.path(),
        "mm-a",
        &[
            user(1, "alpha one"),
            user(2, "alpha two"),
            user(3, "alpha three"),
        ],
    );
    s.index
        .catch_up(&s.dir.path().join("sessions"), &s.store.path("notes.md"))
        .unwrap();
    let got = ask(&s, "alpha", 2);
    assert_eq!(got.text.lines().filter(|l| l.starts_with('[')).count(), 2);
    assert_eq!((got.class, got.untrusted), (DataClass::Private, false));
    let none = ask(&s, "zebra", 5);
    assert_eq!(none.text, "(no matches for \"zebra\")");
    assert_eq!(ask(&s, "NEAR(", 5).text, "(no matches for \"NEAR(\")");
}

#[test]
fn long_hits_are_cut() {
    let s = setup("recall-long");
    // 64 words of 40 letters: longer than 600 characters even after `snippet` keeps 64 words.
    let long = format!("needle {}", format!("{} ", "w".repeat(40)).repeat(100));
    write_log(s.dir.path(), "mm-a", &[user(1, &long)]);
    s.index
        .catch_up(&s.dir.path().join("sessions"), &s.store.path("notes.md"))
        .unwrap();
    let got = ask(&s, "needle", 1);
    let body = got.text.split_once('\n').unwrap().1;
    assert!(body.chars().count() <= 600, "{}", body.chars().count());
}

#[test]
fn every_recall_is_logged_with_its_hits() {
    let s = setup("recall-log");
    write_log(s.dir.path(), "mm-a", &[user(1, "found me")]);
    s.index
        .catch_up(&s.dir.path().join("sessions"), &s.store.path("notes.md"))
        .unwrap();
    ask(&s, "found", 5);
    ask(&s, "missing", 5);
    let log = std::fs::read_to_string(s.store.path("recalls/2026-09.jsonl")).unwrap();
    let lines: Vec<serde_json::Value> = log
        .lines()
        .map(|l| serde_json::from_str(l).unwrap())
        .collect();
    assert_eq!(lines.len(), 2);
    assert_eq!(lines[0]["query"], "found");
    assert_eq!(lines[0]["session"], "mm-now");
    assert_eq!(lines[0]["hits"][0]["session"], "mm-a");
    assert_eq!(lines[0]["hits"][0]["record"], 0);
    assert_eq!(lines[1]["hits"], serde_json::json!([]));
}

#[test]
fn bad_arguments_are_refused() {
    let s = setup("recall-bad");
    let args = RecallArgs {
        query: String::new(),
        k: 5,
    };
    assert!(recall(&s.index, &s.store, &args, "mm-now", now()).is_err());
}