memoryd: recall's local items on one indented line, as Honcho's

Co-Authored-By: ornith-1.5-35b-a3b <agent@wntrmute.dev>

crates/memoryd/src/recall.rs

@@ -3,6 +3,7 @@
 
 use serde::Serialize;
 
+use bxcore::sanitize::neutralise;
 use bxcore::{DataClass, RecallArgs, Timestamp};
 use rusqlite::params;
 
@@ -20,6 +21,38 @@ pub struct Recalled {
     pub untrusted: bool,
 }
 
+/// The local index's hits, each rendered as an item, numbered from 1, and the label they give
+/// the answer: `Private` and trusted when there are none.
+#[derive(Debug, Clone, PartialEq, Eq)]
+pub struct Local {
+    pub items: Vec<String>,
+    pub class: DataClass,
+    pub untrusted: bool,
+}
+
+/// A hit's text as an item holds it, from the local index or from Honcho: neutralised, every
+/// control character (a line break among them) and every Unicode line or paragraph separator a
+/// space, then cut to its first `SNIPPET` characters, with no mark.
+pub fn snippet(text: &str) -> String {
+    neutralise(text)
+        .chars()
+        .map(|c| {
+            if c.is_control() || c == '\u{2028}' || c == '\u{2029}' {
+                ' '
+            } else {
+                c
+            }
+        })
+        .take(SNIPPET)
+        .collect()
+}
+
+/// An item as the model reads it: its header, then its text on one line indented by two spaces,
+/// so that no text can begin a line the way a header does (M5c spec, section 8; tip T37).
+pub fn item(header: &str, text: &str) -> String {
+    format!("{header}\n  {text}")
+}
+
 /// The FTS5 query for `query`: every run of letters and digits, double-quoted, joined by `OR`.
 /// `None` when there is no such run.
 pub fn terms(query: &str) -> Option<String> {
@@ -140,18 +173,39 @@ pub fn recall(
     session: &str,
     now: Timestamp,
 ) -> Result<Recalled, String> {
+    let found = local(index, store, args, session, now)?;
+    if found.items.is_empty() {
+        return Ok(Recalled {
+            text: format!("(no matches for \"{}\")", args.query),
+            class: DataClass::Private,
+            untrusted: false,
+        });
+    }
+    Ok(Recalled {
+        text: found.items.join("\n"),
+        class: found.class,
+        untrusted: found.untrusted,
+    })
+}
+
+/// Search the local index for `args` on behalf of `session`, log the recall, and give its hits
+/// as items with their label. `recall` answers with them alone; with Honcho, its hits follow.
+pub fn local(
+    index: &Index,
+    store: &Store,
+    args: &RecallArgs,
+    session: &str,
+    now: Timestamp,
+) -> Result<Local, String> {
     // 1. `args.check()?`.
     // 2. hits: `terms(&args.query)` None -> none; Some(fts) -> `search(index, &fts, args.k)?`.
     // 3. Log it: a Logged { time: now.to_rfc3339(), session, query, hits: a LoggedHit (kind,
     //    session, epoch, record) per hit } as one JSON line appended to
     //    format!("recalls/{month}.jsonl") (month: the first 7 characters of now.to_rfc3339()),
     //    after `create_dir_all(store.path("recalls"))`.
-    // 4. No hits: Ok(Recalled { text: format!("(no matches for \"{}\")", args.query), class
-    //    Private, untrusted false }).
-    // 5. Otherwise, for each hit with i from 0: class = class.max(its class) starting at Private;
-    //    untrusted |= its tag is "memory-tainted"; its text cut to its first SNIPPET characters;
-    //    the item is format!("{}\n{text}", hit.header(i + 1)). Ok(Recalled { the items joined by
-    //    newlines, class, untrusted }).
+    // 4. For each hit with i from 0: class = class.max(its class) starting at Private;
+    //    untrusted |= its tag is "memory-tainted"; the item is `item(&hit.header(i + 1),
+    //    &snippet(&hit.text))`. Ok(Local { items, class, untrusted }).
     args.check()?;
     let hits: Vec<Hit> = match terms(&args.query) {
         None => Vec::new(),
@@ -176,24 +230,16 @@ pub fn recall(
     };
     let line = serde_json::to_string(&logged).map_err(|e| format!("recall: {e}"))?;
     store.append(&format!("recalls/{month}.jsonl"), &format!("{line}\n"))?;
-    if hits.is_empty() {
-        return Ok(Recalled {
-            text: format!("(no matches for \"{}\")", args.query),
-            class: DataClass::Private,
-            untrusted: false,
-        });
-    }
     let mut class = DataClass::Private;
     let mut untrusted = false;
     let mut items: Vec<String> = Vec::with_capacity(hits.len());
     for (i, hit) in hits.iter().enumerate() {
         class = class.max(hit.class);
         untrusted |= hit.tag() == "memory-tainted";
-        let text: String = hit.text.chars().take(SNIPPET).collect();
-        items.push(format!("{}\n{text}", hit.header(i + 1)));
+        items.push(item(&hit.header(i + 1), &snippet(&hit.text)));
     }
-    Ok(Recalled {
-        text: items.join("\n"),
+    Ok(Local {
+        items,
         class,
         untrusted,
     })