refactor: rename Mode variants C/A to Lexical/Hybrid (closes #2)

The retrieval-mode enum used opaque single letters `Mode { C, A }`;
neither the identifier nor the operator-facing `--mode a` token
conveyed what the mode does. Rename to self-describing names that map
directly onto the glossary definitions:

  Mode::C -> Mode::Lexical  (BM25 + tag filter, offline, no IONOS)
  Mode::A -> Mode::Hybrid   (lexical u semantic -> RRF -> rerank)

Decisions taken (the issue's open questions, resolved):
- CLI canonical tokens are now `lexical` / `hybrid`; the default is
  `lexical`. The legacy `c` / `a` tokens stay accepted as
  case-insensitive input aliases (zero cost; protects hand-typed
  invocations). A unit test pins the alias contract.
- The diagnostics `mode` string (Debug-derived) now emits
  "Lexical"/"Hybrid". Verified safe: no downstream consumer parses it.
  doctate is the future integrator and embeds the library (the `Mode`
  enum), not the JSON string (design spec §103).
- The reserved, out-of-scope generative tier (spec's "Mode B") keeps
  conceptual room: a future `Mode::Generative` does not collide with
  the retrieval-strategy names Lexical/Hybrid.

Surface: enum + FromStr, CLI defaults and `eval --mode both`
expansion, the private `collect_mode_c`/`collect_mode_a` methods (now
`collect_lexical`/`collect_hybrid`) and their comments, the two
pipeline mode test files (renamed), the eval CLI test, the glossary
(old letter forms demoted to Avoid lists), and the spec CLI synopsis.

closes #2

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-31 19:15:08 +02:00
parent 9a81f9eaf7
commit d83b10f939
10 changed files with 68 additions and 41 deletions
+11 -11
View File
@@ -38,8 +38,8 @@ impl Pipeline {
m
};
// Build the semantic index only if EVERY corpus entry already has a
// cached embedding; otherwise leave it `None` so Mode A degrades to C
// rather than mispairing partial vectors.
// cached embedding; otherwise leave it `None` so Mode Hybrid degrades to
// Lexical rather than mispairing partial vectors.
let vector = match EmbeddingStore::open(&cfg.index_dir, &cfg.embed_model) {
Ok(store) if entries.iter().all(|e| store.has(&e.text)) => {
let vecs: Option<Vec<Vec<f32>>> =
@@ -108,9 +108,9 @@ impl Pipeline {
})
}
/// Mode C candidate collection: lexical pool per segment. This is the
/// exact original behavior; it is also the degrade fallback for Mode A.
fn collect_mode_c(&self, segments: &[String]) -> Vec<Candidate> {
/// Mode Lexical candidate collection: lexical pool per segment. This is the
/// exact original behavior; it is also the degrade fallback for Mode Hybrid.
fn collect_lexical(&self, segments: &[String]) -> Vec<Candidate> {
let mut candidates: Vec<Candidate> = Vec::new();
for (si, seg) in segments.iter().enumerate() {
let lex = self.lexical.search(seg, self.pool_size).unwrap_or_default();
@@ -131,11 +131,11 @@ impl Pipeline {
candidates
}
/// Mode A candidate collection: per segment, fuse a lexical pool with a
/// Mode Hybrid candidate collection: per segment, fuse a lexical pool with a
/// semantic pool (IONOS embedding + in-RAM vector search) via RRF, then
/// cross-encoder rerank the fused pool. ANY error (IONOS unreachable, no
/// vector index, embed/rerank failure) propagates so `suggest` degrades.
fn collect_mode_a(&self, segments: &[String], calls: &mut usize)
fn collect_hybrid(&self, segments: &[String], calls: &mut usize)
-> Result<Vec<Candidate>, AppError> {
let client = IonosClient::new(&self.cfg.ionos_base_url, &self.cfg.token_path)?;
let vector = self.vector.as_ref()
@@ -199,14 +199,14 @@ impl Pipeline {
let mut degraded = false;
let candidates: Vec<Candidate> = match mode {
Mode::C => self.collect_mode_c(&segments),
Mode::A => match self.collect_mode_a(&segments, &mut ionos_calls) {
Mode::Lexical => self.collect_lexical(&segments),
Mode::Hybrid => match self.collect_hybrid(&segments, &mut ionos_calls) {
Ok(c) => c,
Err(_) => {
// Total degradation: any failure → Mode C fallback,
// Total degradation: any failure → Mode Lexical fallback,
// request still answered, never panics.
degraded = true;
self.collect_mode_c(&segments)
self.collect_lexical(&segments)
}
},
};