@polycode-projects/the-mechanical-code-talker 0.9.2 → 0.9.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@polycode-projects/the-mechanical-code-talker",
|
|
3
|
-
"version": "0.9.
|
|
3
|
+
"version": "0.9.3",
|
|
4
4
|
"private": false,
|
|
5
5
|
"type": "module",
|
|
6
6
|
"description": "The Mechanical Code Talker (tmct) — a tolerant, offline, $0 chat surface that guides you toward precision queries about a software repository. ELIZA/PARRY-style but domain-obsessed with code. No model calls; no codebase index of its own.",
|
|
@@ -485,6 +485,12 @@ export const STOPWORDS = new Set([
|
|
|
485
485
|
// literally named "last" would be the accepted residual cost, same trade as
|
|
486
486
|
// every other stopword.
|
|
487
487
|
"last",
|
|
488
|
+
// frequency-adverb filler ("what does X usually change together with", "what does
|
|
489
|
+
// X typically call") — found live: "usually" glued onto the object term instead of
|
|
490
|
+
// being stripped, corrupting resolution ("src/core/store.mjs usually" instead of
|
|
491
|
+
// the module alone). Same trade as every other stopword: a symbol literally named
|
|
492
|
+
// "usually" would be the accepted residual cost.
|
|
493
|
+
"usually", "typically", "generally", "normally", "often", "commonly", "mostly",
|
|
488
494
|
]);
|
|
489
495
|
|
|
490
496
|
/** Split free text into words: trailing "?" run stripped, commas treated as
|
|
@@ -150,6 +150,21 @@ export function parseKeywordSpot(text, nlp = null) {
|
|
|
150
150
|
const consumed = new Set();
|
|
151
151
|
const mark = (hit) => { if (hit) for (let i = hit.start; i < hit.end; i += 1) consumed.add(i); };
|
|
152
152
|
mark(verbHit);
|
|
153
|
+
// A redundant SAME-KIND verb immediately after the matched one ("what TESTS
|
|
154
|
+
// cover X" — "tests" is read as the relation trigger, but "cover" — also a
|
|
155
|
+
// `tests` verb, ask-vocab.mjs's own synonym list — is the word the sentence
|
|
156
|
+
// actually intends as the verb) would otherwise fall into afterText raw and
|
|
157
|
+
// corrupt the object ("cover src/core/model.mjs" instead of the module alone).
|
|
158
|
+
// Anchored to the exact position right after verbHit (never a general re-scan),
|
|
159
|
+
// and gated on matching the SAME kind, so this can only strip a genuine
|
|
160
|
+
// restatement, never eat a real object term. Found live: "what tests cover X",
|
|
161
|
+
// "which tests test X" both misparsed this way before this fix.
|
|
162
|
+
for (const [phrase, kind] of Object.entries(VERB_TO_KIND)) {
|
|
163
|
+
if (kind !== verbHit.kind) continue;
|
|
164
|
+
const pWords = phrase.split(" ");
|
|
165
|
+
const start = verbHit.end;
|
|
166
|
+
if (pWords.every((w, j) => canonWords[start + j] === w)) { mark({ start, end: start + pWords.length }); break; }
|
|
167
|
+
}
|
|
153
168
|
const entityHit = findPhrase(canonWords, ENTITY_TO_TYPE, consumed);
|
|
154
169
|
mark(entityHit);
|
|
155
170
|
const modifierHit = findPhrase(canonWords, MODIFIER_TO_KIND, consumed);
|