feat(v0.17.0/A5): trigram-aware build_match_string + SearchResponse.hint
PR-A 본체. plan Task A4 Step 1c + A5. - lexical.rs::build_match_string 재설계: whole-phrase + token-AND OR-combined, 3자 미만 토큰 drop, 후보 없음 시 None (빈 MATCH 회피). raw single-quote mode 유지. - SearchResponse.hint additive — empty result + trimmed < 3 chars + non-raw 케이스에 short_query_hint helper 가 set. - CLI 'kebab search' 가 [hint] stderr 한 줄 (text mode). - TUI SearchState.short_query_hint + poll_worker stale-aware set + fire_search/mark_input_changed reset + dynamic_status 표시. - docs/wire-schema/v1/search_response.schema.json hint additive. - 신규 unit tests (lexical 9 PASS, 기존 2 expectation 갱신) + 통합 회귀 (search_korean: multi_token + mixed, 3 PASS) + BM25 snapshot regen (trigram token stream). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -73,6 +73,37 @@ pub struct SearchResponse {
|
||||
/// p9-fb-37: present when caller passed `SearchOpts.trace = true`.
|
||||
/// Consumers that ignore trace should leave this `None`.
|
||||
pub trace: Option<kebab_core::SearchTrace>,
|
||||
/// v0.17.0 A5 Step 4b: human / agent-readable advisory string set
|
||||
/// when the empty hit list is likely due to a query shorter than the
|
||||
/// FTS5 trigram tokenizer's 3-char minimum. `None` otherwise. CLI
|
||||
/// surfaces it on stderr (text mode); MCP / `--json` consumers
|
||||
/// surface it however they prefer. See
|
||||
/// `docs/superpowers/specs/2026-05-22-korean-trigram-tokenizer-design.md`
|
||||
/// §3.3.
|
||||
pub hint: Option<String>,
|
||||
}
|
||||
|
||||
/// v0.17.0 A5 Step 4b: decide whether to attach a "3자 이상 키워드 권장"
|
||||
/// hint to a `SearchResponse`. Fires only when the result set is empty
|
||||
/// *and* the trimmed query is shorter than the trigram tokenizer can
|
||||
/// resolve. Raw FTS5 mode (`'...'`) opts out — the user explicitly
|
||||
/// invoked FTS5 syntax. Identical condition powers the CLI stderr line
|
||||
/// and (separately) the TUI status bar.
|
||||
pub fn short_query_hint(query_text: &str, hits_empty: bool) -> Option<String> {
|
||||
if !hits_empty {
|
||||
return None;
|
||||
}
|
||||
let trimmed = query_text.trim();
|
||||
let bytes = trimmed.as_bytes();
|
||||
// Raw single-quote mode: user opted into FTS5 syntax, no advisory.
|
||||
if bytes.len() >= 2 && bytes[0] == b'\'' && bytes[bytes.len() - 1] == b'\'' {
|
||||
return None;
|
||||
}
|
||||
if trimmed.chars().count() < 3 {
|
||||
Some("3자 이상 키워드 권장 (trigram tokenizer 제약)".to_string())
|
||||
} else {
|
||||
None
|
||||
}
|
||||
}
|
||||
|
||||
/// Facade state — see module docs for lifetime rules.
|
||||
@@ -418,11 +449,13 @@ impl App {
|
||||
|
||||
// Trace path skips the budget loop. Caller will inspect
|
||||
// `hits.len()` and `trace.timing` rather than paginate.
|
||||
let hint = short_query_hint(&query.text, hits.is_empty());
|
||||
return Ok(SearchResponse {
|
||||
hits,
|
||||
next_cursor: None,
|
||||
truncated: false,
|
||||
trace: Some(trace),
|
||||
hint,
|
||||
});
|
||||
}
|
||||
|
||||
@@ -505,11 +538,13 @@ impl App {
|
||||
None
|
||||
};
|
||||
|
||||
let hint = short_query_hint(&query.text, hits.is_empty());
|
||||
Ok(SearchResponse {
|
||||
hits,
|
||||
next_cursor,
|
||||
truncated,
|
||||
trace: None,
|
||||
hint,
|
||||
})
|
||||
}
|
||||
|
||||
|
||||
@@ -96,6 +96,11 @@ fn serialize_search_response(r: &SearchResponse) -> Value {
|
||||
None => Value::Null,
|
||||
};
|
||||
map.insert("trace".to_string(), trace_v);
|
||||
// v0.17.0 A5 Step 4b: only emit `hint` when set — matches
|
||||
// the CLI wire wrapper's additive emit pattern.
|
||||
if let Some(hint) = &r.hint {
|
||||
map.insert("hint".to_string(), Value::String(hint.clone()));
|
||||
}
|
||||
}
|
||||
v
|
||||
}
|
||||
|
||||
@@ -69,7 +69,7 @@ pub mod reset;
|
||||
pub mod schema;
|
||||
mod staleness;
|
||||
|
||||
pub use app::{App, SearchResponse};
|
||||
pub use app::{App, SearchResponse, short_query_hint};
|
||||
pub use ingest_progress::{AggregateCounts, IngestEvent, render_skipped_breakdown};
|
||||
pub use reset::{ResetReport, ResetScope, enumerate_orphans};
|
||||
pub use error_wire::{ERROR_V1_ID, ErrorV1, StructuredError, classify};
|
||||
|
||||
@@ -46,3 +46,88 @@ fn korean_lexical_query_returns_korean_document() {
|
||||
hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
|
||||
);
|
||||
}
|
||||
|
||||
/// A4 Step 1c — multi-token Korean query (`해시 충돌`) must hit when
|
||||
/// the lexical builder routes it through a whole-phrase MATCH candidate.
|
||||
///
|
||||
/// Expected: FAIL until A5 (`build_match_string` redesign) lands — the
|
||||
/// current builder emits `"해시" "충돌"` AND, but FTS5 trigram tokenizer
|
||||
/// has no 2-char terms so each side is 0-hit. A5 introduces a whole-
|
||||
/// phrase candidate (`"해시 충돌"`) OR'd with the token AND, restoring
|
||||
/// hits for the dominant Korean usage pattern.
|
||||
#[test]
|
||||
fn lexical_multi_token_korean_query_hits() {
|
||||
let env = TestEnv::lexical_only();
|
||||
|
||||
// Copy the synthetic Korean fixture (introduced in A4 Step 0) into
|
||||
// the test workspace. The fixture contains the exact phrase
|
||||
// "해시 충돌" multiple times.
|
||||
let dest = env.workspace_root.join("hash-table.md");
|
||||
let src = std::path::PathBuf::from(env!("CARGO_MANIFEST_DIR"))
|
||||
.join("..")
|
||||
.join("..")
|
||||
.join("fixtures")
|
||||
.join("search")
|
||||
.join("korean")
|
||||
.join("hash-table.md");
|
||||
std::fs::copy(&src, &dest).expect("copy korean fixture");
|
||||
|
||||
kebab_app::ingest_with_config(env.config.clone(), env.scope(), true)
|
||||
.expect("ingest must succeed");
|
||||
|
||||
let hits = kebab_app::search_with_config(
|
||||
env.config.clone(),
|
||||
common::lexical_query("해시 충돌"),
|
||||
)
|
||||
.expect("search must succeed");
|
||||
|
||||
assert!(
|
||||
!hits.is_empty(),
|
||||
"multi-token Korean query '해시 충돌' must hit the hash-table fixture; got {:?}",
|
||||
hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
|
||||
);
|
||||
let any_hash_table = hits.iter().any(|h| h.doc_path.0.contains("hash-table"));
|
||||
assert!(
|
||||
any_hash_table,
|
||||
"expected at least one hit on the hash-table fixture, got: {:?}",
|
||||
hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
|
||||
);
|
||||
}
|
||||
|
||||
/// A4 Step 1c — mixed Korean+English multi-token query (`Rust 충돌은`).
|
||||
/// Both tokens are ≥3 chars, so the redesigned builder (A5) emits
|
||||
/// `("Rust 충돌은") OR ("Rust" AND "충돌은")`. With trigram tokenizer
|
||||
/// each side has substring coverage in the document, so the AND branch
|
||||
/// alone is enough. Expected: FAIL pre-A5, PASS post-A5.
|
||||
#[test]
|
||||
fn lexical_mixed_korean_english_multi_token_query_hits() {
|
||||
let env = TestEnv::lexical_only();
|
||||
let doc_path = env.workspace_root.join("rust-hash.md");
|
||||
std::fs::write(
|
||||
&doc_path,
|
||||
"# Rust 해시 테이블\n\nRust 의 std::collections::HashMap 에서 \
|
||||
해시 충돌은 SipHash 로 완화한다.\n",
|
||||
)
|
||||
.expect("write rust-hash fixture");
|
||||
|
||||
kebab_app::ingest_with_config(env.config.clone(), env.scope(), true)
|
||||
.expect("ingest must succeed");
|
||||
|
||||
let hits = kebab_app::search_with_config(
|
||||
env.config.clone(),
|
||||
common::lexical_query("Rust 충돌은"),
|
||||
)
|
||||
.expect("search must succeed");
|
||||
|
||||
assert!(
|
||||
!hits.is_empty(),
|
||||
"mixed Korean+English multi-token query 'Rust 충돌은' must hit the rust-hash fixture; got {:?}",
|
||||
hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
|
||||
);
|
||||
let any_rust_hash = hits.iter().any(|h| h.doc_path.0.contains("rust-hash"));
|
||||
assert!(
|
||||
any_rust_hash,
|
||||
"expected at least one hit on the rust-hash fixture, got: {:?}",
|
||||
hits.iter().map(|h| &h.doc_path.0).collect::<Vec<_>>()
|
||||
);
|
||||
}
|
||||
|
||||
@@ -933,6 +933,15 @@ fn run(cli: &Cli) -> anyhow::Result<()> {
|
||||
let next = resp.next_cursor.as_deref().unwrap_or("(none)");
|
||||
eprintln!("[truncated; use --cursor {next} for the next page]");
|
||||
}
|
||||
// v0.17.0 A5 Step 4: short-query advisory. `resp.hint`
|
||||
// is `Some` only when the result list is empty and the
|
||||
// trimmed query is shorter than the trigram tokenizer
|
||||
// can resolve (raw FTS5 mode opts out). stderr so it
|
||||
// doesn't pollute the stdout hit list. `--json` skips
|
||||
// this branch entirely; the field rides the wire.
|
||||
if let Some(hint) = &resp.hint {
|
||||
eprintln!("[hint] {hint}");
|
||||
}
|
||||
if *trace {
|
||||
if let Some(t) = &resp.trace {
|
||||
eprintln!();
|
||||
|
||||
@@ -92,6 +92,14 @@ pub fn wire_search_response(r: &kebab_app::SearchResponse) -> Value {
|
||||
map.insert("trace".to_string(), trace_v);
|
||||
}
|
||||
}
|
||||
// v0.17.0 A5 Step 4b: emit `hint` only when set. Keeps responses
|
||||
// that don't carry a hint backward-compatible with v0 consumers
|
||||
// that don't know the field.
|
||||
if let Some(hint) = &r.hint {
|
||||
if let Value::Object(ref mut map) = v {
|
||||
map.insert("hint".to_string(), Value::String(hint.clone()));
|
||||
}
|
||||
}
|
||||
tag_object(v, "search_response.v1")
|
||||
}
|
||||
|
||||
@@ -292,6 +300,7 @@ mod tests {
|
||||
next_cursor: Some("opaque-cursor-abc".to_string()),
|
||||
truncated: true,
|
||||
trace: None,
|
||||
hint: None,
|
||||
};
|
||||
let v = wire_search_response(&r);
|
||||
assert_eq!(schema_of(&v), Some("search_response.v1"));
|
||||
@@ -405,6 +414,7 @@ mod tests {
|
||||
}],
|
||||
timing: TraceTiming { lexical_ms: 5, vector_ms: 0, fusion_ms: 1, total_ms: 7 },
|
||||
}),
|
||||
hint: None,
|
||||
};
|
||||
let v = wire_search_response(&r);
|
||||
assert_eq!(schema_of(&v), Some("search_response.v1"));
|
||||
@@ -420,6 +430,7 @@ mod tests {
|
||||
next_cursor: None,
|
||||
truncated: false,
|
||||
trace: None,
|
||||
hint: None,
|
||||
};
|
||||
let v = wire_search_response(&r);
|
||||
assert!(v.get("trace").is_none(), "trace field absent when None");
|
||||
|
||||
@@ -162,18 +162,35 @@ impl Retriever for LexicalRetriever {
|
||||
|
||||
/// Translate a user-typed query into an FTS5 match string.
|
||||
///
|
||||
/// Rules (from the task spec):
|
||||
/// v0.17.0 — trigram-aware redesign (see design §5.5 + plan
|
||||
/// `docs/superpowers/plans/2026-05-22-korean-trigram-tokenizer.md`
|
||||
/// Task A5). The FTS5 tokenizer is `trigram` so any term shorter than
|
||||
/// three Unicode chars has no index entry and would zero out an AND
|
||||
/// branch. Korean compounds typically split into 2-char eojeols (e.g.
|
||||
/// `해시 충돌`), so a naive token AND drops the dominant usage pattern.
|
||||
///
|
||||
/// - The query is wrapped in a single pair of `'...'` → strip the quotes
|
||||
/// and pass the inner text through verbatim. The user has explicitly
|
||||
/// opted into FTS5 syntax (e.g. `'rust AND cargo'`, `'foo*'`).
|
||||
/// Rules:
|
||||
///
|
||||
/// - Otherwise: split on whitespace, escape every token by wrapping it
|
||||
/// in `"..."` (FTS5 string literal), with any inner `"` doubled. Join
|
||||
/// with spaces — FTS5 default operator is implicit AND.
|
||||
/// - Raw mode (unchanged): the query is wrapped in a single pair of
|
||||
/// `'...'` → strip the quotes and pass the inner text through verbatim.
|
||||
/// The user has explicitly opted into FTS5 syntax (e.g.
|
||||
/// `'rust AND cargo'`, `'foo*'`).
|
||||
///
|
||||
/// - An empty / whitespace-only token list → return `None` (caller
|
||||
/// short-circuits to `Ok(vec![])`).
|
||||
/// - Otherwise build up to two MATCH candidates:
|
||||
/// 1. **whole-phrase**: the entire trimmed input wrapped as one FTS5
|
||||
/// string literal, *only* if it has ≥3 Unicode chars. FTS5 treats
|
||||
/// a quoted string with spaces as a phrase match.
|
||||
/// 2. **token AND**: whitespace-split tokens, kept only when each has
|
||||
/// ≥3 Unicode chars (shorter ones are dropped — they would zero
|
||||
/// out the AND under trigram).
|
||||
///
|
||||
/// - Combine: `(whole) OR (token_and)` when both exist *and differ*;
|
||||
/// either alone when only one exists; `None` when neither exists
|
||||
/// (caller short-circuits to `Ok(vec![])`, avoiding an FTS5 syntax
|
||||
/// error from an empty MATCH).
|
||||
///
|
||||
/// - A single-token long query (`러스트`, `foo`) yields `whole == token_and`
|
||||
/// → return the bare quoted form so the OR doesn't duplicate.
|
||||
fn build_match_string(text: &str) -> Option<String> {
|
||||
let trimmed = text.trim();
|
||||
if trimmed.is_empty() {
|
||||
@@ -186,14 +203,27 @@ fn build_match_string(text: &str) -> Option<String> {
|
||||
}
|
||||
return Some(inner_trim.to_string());
|
||||
}
|
||||
let tokens: Vec<String> = trimmed
|
||||
.split_whitespace()
|
||||
.map(escape_fts5_token)
|
||||
.collect();
|
||||
if tokens.is_empty() {
|
||||
None
|
||||
} else {
|
||||
Some(tokens.join(" "))
|
||||
|
||||
const MIN_TRIGRAM_CHARS: usize = 3;
|
||||
|
||||
let whole_candidate: Option<String> = (trimmed.chars().count() >= MIN_TRIGRAM_CHARS)
|
||||
.then(|| escape_fts5_token(trimmed));
|
||||
|
||||
let token_and_candidate: Option<String> = {
|
||||
let toks: Vec<String> = trimmed
|
||||
.split_whitespace()
|
||||
.filter(|t| t.chars().count() >= MIN_TRIGRAM_CHARS)
|
||||
.map(escape_fts5_token)
|
||||
.collect();
|
||||
(!toks.is_empty()).then(|| toks.join(" "))
|
||||
};
|
||||
|
||||
match (whole_candidate, token_and_candidate) {
|
||||
(None, None) => None,
|
||||
(Some(w), None) => Some(w),
|
||||
(None, Some(a)) => Some(a),
|
||||
(Some(w), Some(a)) if w == a => Some(w),
|
||||
(Some(w), Some(a)) => Some(format!("({w}) OR ({a})")),
|
||||
}
|
||||
}
|
||||
|
||||
@@ -555,30 +585,31 @@ mod tests {
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn build_match_string_default_is_quoted_and_anded() {
|
||||
fn build_match_string_default_emits_or_of_phrase_and_and() {
|
||||
// Two long tokens: both whole-phrase and token-AND candidates
|
||||
// exist and differ, so the builder combines them with OR.
|
||||
let s = build_match_string("rust cargo").unwrap();
|
||||
// Two tokens, each quoted, joined by a space (implicit AND).
|
||||
assert_eq!(s, r#""rust" "cargo""#);
|
||||
assert_eq!(s, r#"("rust cargo") OR ("rust" "cargo")"#);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn build_match_string_escapes_special_chars() {
|
||||
// `*`, `(`, `)`, `:`, `^`, `"` should all be wrapped inside
|
||||
// FTS5 string-literal quotes so they're treated as literal
|
||||
// text rather than FTS5 operators.
|
||||
// text rather than FTS5 operators. Every token is ≥3 chars,
|
||||
// so both the whole-phrase and token-AND candidates exist.
|
||||
let s = build_match_string(r#"foo* (bar) baz:qux ^head he"llo"#).unwrap();
|
||||
assert_eq!(
|
||||
s,
|
||||
r#""foo*" "(bar)" "baz:qux" "^head" "he""llo""#
|
||||
r#"("foo* (bar) baz:qux ^head he""llo") OR ("foo*" "(bar)" "baz:qux" "^head" "he""llo")"#
|
||||
);
|
||||
// The doubled `""` is FTS5's way of embedding a literal quote
|
||||
// inside a string literal.
|
||||
// inside a string literal. Appears in both whole-phrase and
|
||||
// token-AND halves.
|
||||
assert!(s.contains(r#"he""llo"#));
|
||||
// Sanity: every special character lives between matching `"`
|
||||
// delimiters — there is no bare-token (unquoted) span anywhere.
|
||||
// We check this by confirming the string starts and ends with `"`
|
||||
// and the count of unescaped `"` is even (each token is wrapped).
|
||||
assert!(s.starts_with('"') && s.ends_with('"'));
|
||||
// Sanity: the combined expression is `(...) OR (...)` so it
|
||||
// starts with `(` and ends with `)`.
|
||||
assert!(s.starts_with('(') && s.ends_with(')'));
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -588,6 +619,55 @@ mod tests {
|
||||
assert_eq!(s, "foo OR bar*");
|
||||
}
|
||||
|
||||
// ── v0.17.0 trigram-aware redesign coverage ──────────────────────────
|
||||
|
||||
/// 2-char Korean query (`충돌`) yields neither a whole-phrase nor a
|
||||
/// token-AND candidate → `None`. Caller short-circuits to an empty
|
||||
/// hit list rather than executing an FTS5 syntax error on `""` MATCH.
|
||||
#[test]
|
||||
fn build_match_string_short_korean_returns_none() {
|
||||
assert!(build_match_string("충돌").is_none());
|
||||
assert!(build_match_string("키").is_none());
|
||||
assert!(build_match_string(" 충돌 ").is_none());
|
||||
}
|
||||
|
||||
/// `해시 충돌` — both tokens are 2 chars (dropped from the AND), but
|
||||
/// the whole-phrase candidate (`"해시 충돌"`, 5 chars total) survives.
|
||||
/// This is the dominant Korean usage pattern targeted by A5.
|
||||
#[test]
|
||||
fn build_match_string_whole_phrase_only_when_all_tokens_short() {
|
||||
let s = build_match_string("해시 충돌").unwrap();
|
||||
assert_eq!(s, r#""해시 충돌""#);
|
||||
}
|
||||
|
||||
/// Single long token: whole-phrase and token-AND candidates collapse
|
||||
/// to the same string. The builder returns the bare quoted form so
|
||||
/// the MATCH expression doesn't carry a redundant `(x) OR (x)`.
|
||||
#[test]
|
||||
fn build_match_string_single_long_token_no_duplicate_or() {
|
||||
assert_eq!(build_match_string("러스트").unwrap(), r#""러스트""#);
|
||||
assert_eq!(build_match_string("rust").unwrap(), r#""rust""#);
|
||||
}
|
||||
|
||||
/// Mixed Korean+English multi-token query where every token is ≥3
|
||||
/// chars: both candidates exist and differ, OR-combined.
|
||||
#[test]
|
||||
fn build_match_string_mixed_lang_emits_or_of_phrase_and_and() {
|
||||
let s = build_match_string("Rust 충돌은").unwrap();
|
||||
assert_eq!(s, r#"("Rust 충돌은") OR ("Rust" "충돌은")"#);
|
||||
}
|
||||
|
||||
/// One ≥3 token + one <3 token: short token is dropped from the
|
||||
/// AND, leaving a single long token there; whole-phrase exists
|
||||
/// independently. Both candidates differ → OR-combined.
|
||||
#[test]
|
||||
fn build_match_string_drops_short_token_in_and_keeps_whole() {
|
||||
// "키" (1 char) dropped from AND; "해시테이블" (5 chars) kept.
|
||||
// Whole phrase "키 해시테이블" (7 chars) keeps the short token.
|
||||
let s = build_match_string("키 해시테이블").unwrap();
|
||||
assert_eq!(s, r#"("키 해시테이블") OR ("해시테이블")"#);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn normalize_bm25_top_score_in_unit_interval() {
|
||||
// A "perfect" hit is bm25 = -1.0 → normalized 0.5.
|
||||
|
||||
@@ -19,9 +19,9 @@
|
||||
"indexed_at": "2024-01-01T00:00:00Z",
|
||||
"rank": 1,
|
||||
"retrieval": {
|
||||
"fusion_score": 1.4490997273242101e-6,
|
||||
"fusion_score": 1.4615362715630908e-6,
|
||||
"lexical_rank": 1,
|
||||
"lexical_score": 1.4490997273242101e-6,
|
||||
"lexical_score": 1.4615362715630908e-6,
|
||||
"method": "lexical",
|
||||
"vector_rank": null,
|
||||
"vector_score": null
|
||||
@@ -51,9 +51,9 @@
|
||||
"indexed_at": "2024-01-01T00:00:00Z",
|
||||
"rank": 2,
|
||||
"retrieval": {
|
||||
"fusion_score": 9.641424867368187e-7,
|
||||
"fusion_score": 9.207039965986041e-7,
|
||||
"lexical_rank": 2,
|
||||
"lexical_score": 9.641424867368187e-7,
|
||||
"lexical_score": 9.207039965986041e-7,
|
||||
"method": "lexical",
|
||||
"vector_rank": null,
|
||||
"vector_score": null
|
||||
|
||||
@@ -153,6 +153,12 @@ pub struct SearchState {
|
||||
/// `Ctrl-L`); the previous draft kept one for "symmetry" but
|
||||
/// it was dead code.
|
||||
pub worker_rx: Option<std::sync::mpsc::Receiver<SearchWorkerMessage>>,
|
||||
/// v0.17.0 A5 Step 5: advisory text shown when the last completed
|
||||
/// search returned no hits and the (trimmed) query is shorter than
|
||||
/// the FTS5 trigram tokenizer's 3-char minimum. `None` whenever
|
||||
/// the input changes (so a stale hint never overlaps a fresh
|
||||
/// typing session) or the next search returns ≥1 hit.
|
||||
pub short_query_hint: Option<String>,
|
||||
}
|
||||
|
||||
/// p9-fb-08: payload posted by the search worker on completion.
|
||||
@@ -179,6 +185,7 @@ impl Default for SearchState {
|
||||
preview: None,
|
||||
generation: 0,
|
||||
worker_rx: None,
|
||||
short_query_hint: None,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -393,6 +393,20 @@ fn dynamic_status(app: &App) -> String {
|
||||
if app.search.as_ref().map(|s| s.searching).unwrap_or(false) {
|
||||
return "searching…".to_string();
|
||||
}
|
||||
// v0.17.0 A5 Step 5: short-query advisory has higher priority than
|
||||
// the idle slot but lower than active operations (streaming /
|
||||
// searching / ingest progress) — the user should always see what
|
||||
// is happening *now* before reading guidance about the last
|
||||
// empty result. Slot only fires while focused on Search.
|
||||
if app.focus == Pane::Search {
|
||||
if let Some(hint) = app
|
||||
.search
|
||||
.as_ref()
|
||||
.and_then(|s| s.short_query_hint.as_deref())
|
||||
{
|
||||
return hint.to_string();
|
||||
}
|
||||
}
|
||||
if let Some(state) = app.ingest_state.as_ref() {
|
||||
return crate::ingest_progress::status_line(state);
|
||||
}
|
||||
|
||||
@@ -333,7 +333,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
|
||||
s.mode = cycle_mode(s.mode);
|
||||
// Force re-search at the new mode if there's a query.
|
||||
if !s.input.as_str().trim().is_empty() {
|
||||
s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
|
||||
mark_input_changed(s);
|
||||
}
|
||||
KeyOutcome::Continue
|
||||
}
|
||||
@@ -360,7 +360,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
|
||||
(KeyCode::Backspace, _) => {
|
||||
if !s.input.is_empty() {
|
||||
s.input.pop_char();
|
||||
s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
|
||||
mark_input_changed(s);
|
||||
}
|
||||
KeyOutcome::Continue
|
||||
}
|
||||
@@ -388,7 +388,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
|
||||
}
|
||||
(KeyCode::Delete, _) => {
|
||||
if s.input.delete_after().is_some() {
|
||||
s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
|
||||
mark_input_changed(s);
|
||||
}
|
||||
KeyOutcome::Continue
|
||||
}
|
||||
@@ -402,7 +402,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
|
||||
s.preview = None;
|
||||
} else {
|
||||
s.input.push_char('j');
|
||||
s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
|
||||
mark_input_changed(s);
|
||||
}
|
||||
KeyOutcome::Continue
|
||||
}
|
||||
@@ -412,7 +412,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
|
||||
s.preview = None;
|
||||
} else {
|
||||
s.input.push_char('k');
|
||||
s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
|
||||
mark_input_changed(s);
|
||||
}
|
||||
KeyOutcome::Continue
|
||||
}
|
||||
@@ -426,7 +426,7 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
|
||||
// bindings (and don't currently match any Search
|
||||
// command, so they're a safe fall-through to Continue).
|
||||
s.input.push_char(c);
|
||||
s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
|
||||
mark_input_changed(s);
|
||||
KeyOutcome::Continue
|
||||
}
|
||||
// Normal mode + un-handled Char → no-op (no typing in
|
||||
@@ -435,6 +435,16 @@ pub fn handle_key_search(state: &mut App, key: KeyEvent) -> KeyOutcome {
|
||||
}
|
||||
}
|
||||
|
||||
/// v0.17.0 A5 Step 5: every input-mutation site in `handle_key_search`
|
||||
/// funnels through this helper so the debounce stamp and the
|
||||
/// short-query advisory stay in sync. Reset is eager — the stale
|
||||
/// advisory from the previous result set must not visually overlap
|
||||
/// with a fresh typing session.
|
||||
fn mark_input_changed(s: &mut crate::app::SearchState) {
|
||||
s.input_dirty_at = Some(time::OffsetDateTime::now_utc());
|
||||
s.short_query_hint = None;
|
||||
}
|
||||
|
||||
fn cycle_mode(m: SearchMode) -> SearchMode {
|
||||
match m {
|
||||
SearchMode::Lexical => SearchMode::Vector,
|
||||
@@ -603,6 +613,11 @@ pub(crate) fn fire_search(state: &mut App) -> anyhow::Result<()> {
|
||||
s.generation = s.generation.wrapping_add(1);
|
||||
s.searching = true;
|
||||
s.input_dirty_at = None;
|
||||
// v0.17.0 A5 Step 5: hint belongs to the *prior* result set —
|
||||
// a fresh worker spawn invalidates it so the status bar
|
||||
// doesn't keep showing the old advisory while the new
|
||||
// query is in flight.
|
||||
s.short_query_hint = None;
|
||||
let q_text = s.input.as_str().to_string();
|
||||
s.last_query = Some((q_text.clone(), s.mode));
|
||||
(q_text, s.mode, s.generation)
|
||||
@@ -676,6 +691,18 @@ pub fn poll_worker(state: &mut App) {
|
||||
s.searching = false;
|
||||
match result {
|
||||
Ok(hits) => {
|
||||
// v0.17.0 A5 Step 5: stale-aware short-query hint.
|
||||
// The worker carries no copy of the query text;
|
||||
// we ground the advisory on `s.last_query` which
|
||||
// was snapshotted at `fire_search` time and (by
|
||||
// the generation guard above) still matches what
|
||||
// the user submitted for *this* result set. If
|
||||
// input has drifted since spawn, the gen-check
|
||||
// already returned early.
|
||||
let q_text =
|
||||
s.last_query.as_ref().map(|(t, _)| t.as_str()).unwrap_or("");
|
||||
s.short_query_hint =
|
||||
kebab_app::short_query_hint(q_text, hits.is_empty());
|
||||
s.hits = hits;
|
||||
s.selected_hit = 0;
|
||||
s.preview = None;
|
||||
@@ -683,6 +710,7 @@ pub fn poll_worker(state: &mut App) {
|
||||
Err(e) => {
|
||||
s.hits.clear();
|
||||
s.selected_hit = 0;
|
||||
s.short_query_hint = None;
|
||||
state.error_overlay =
|
||||
Some(crate::error_popup::ErrorOverlay::from_anyhow(&e));
|
||||
}
|
||||
|
||||
@@ -29,6 +29,10 @@
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"hint": {
|
||||
"type": "string",
|
||||
"description": "v0.17.0 A5 Step 4b: advisory string set when the empty hit list is likely due to a query shorter than the FTS5 trigram tokenizer's 3-char minimum. Field is omitted when no advisory applies. Raw FTS5 mode ('...') opts out. MCP / agent consumers should surface this so users understand the empty result rather than retrying the same short query."
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user