sigmap 8.4.0 → 8.5.0

package/CHANGELOG.md

@@ -10,6 +10,13 @@ Format: [Semantic Versioning](https://semver.org/)
 
 ---
 
+## [8.5.0] — 2026-07-05
+
+Minor release — **deterministic query expansion (a vocabulary-mismatch recall aid).** The BM25 ranker now bridges common code-domain synonyms/abbreviations so a query for `authentication` can still surface a file whose signatures only say `auth`. Zero-dependency, deterministic. **Honest framing:** measured on the retrieval benchmark, this is **benchmark-neutral** (hit@5 unchanged within the harness's 86.7–87.8% noise band at the shipped weight) — not a hit@5 improvement. The benefit is for real users whose query vocabulary differs from the code, a case the curated benchmark doesn't exercise.
+
+### Added
+- **Query expansion (#421, PR #422):** `src/retrieval/bm25.js` gains a curated, high-precision synonym/abbreviation table (`auth`↔`authentication`/`login`, `db`↔`database`, `ctx`↔`context`, `config`↔`configuration`, `req`/`res`, `init`, `impl`, …). `expandQuery()` adds synonyms to the query tokens at a **discount weight (0.15)** so an exact-term match always outranks a synonym-only match; documents are unchanged. Wired through the ranker, so `sigmap ask`, `--query`, and MCP `query_context` all benefit. A weight sweep confirmed higher weights regress retrieval, so 0.15 (benchmark-neutral) is the shipped setting.
+
 ## [8.4.0] — 2026-07-05
 
 Minor release — **PR Evidence Report (v9.0 G3): a branded, deterministic review artifact.** SigMap already had the pieces — `review-pr` findings and `get_diff_context` — but no single Markdown comment an agent or CI could post on a PR. This adds it: one report that answers *"what changed, what it touches, and what to test"*, with no LLM.

package/README.md

@@ -98,7 +98,7 @@ Ask → Rank → Context → Validate → Judge → Learn
 
 <!--SM:benchmarkBlock-->
 ```
-Benchmark : sigmap-v8.4-main (21 repositories, including R language)
+Benchmark : sigmap-v8.5-main (21 repositories, including R language)
 Date      : 2026-07-04
 
 Hit@5          : 86.7%   (baseline 13.6%  — 6.4× lift)

package/gen-context.js

@@ -13108,7 +13108,7 @@ __factories["./src/mcp/server"] = function(module, exports) {
 
   const SERVER_INFO = {
     name: 'sigmap',
-    version: '8.4.0',
+    version: '8.5.0',
     description: 'SigMap MCP server — code signatures on demand',
   };
 
@@ -13923,6 +13923,78 @@ __factories["./src/retrieval/bm25"] = function(module, exports) {
   // are counted PATH_BOOST times when building the document term-frequency map.
   const PATH_BOOST = 3;
 
+  // Curated, high-precision code-domain synonym / abbreviation expansions. A query
+  // for `authentication` should still surface a file whose signatures only say
+  // `auth`. Kept deliberately tight — over-broad synonyms hurt precision. Groups
+  // are expanded bidirectionally (every member maps to the others). Values are
+  // tokenized+stemmed at load, so entries are written in natural form.
+  const EXPANSION_GROUPS = [
+    ['auth', 'authenticate', 'authentication', 'login', 'signin', 'credential'],
+    ['authorize', 'authorization', 'permission', 'access'],
+    ['config', 'configuration', 'settings', 'options'],
+    ['db', 'database'],
+    ['ctx', 'context'],
+    ['req', 'request'],
+    ['res', 'response'],
+    ['err', 'error'],
+    ['msg', 'message'],
+    ['init', 'initialize', 'initialization', 'setup'],
+    ['async', 'asynchronous'],
+    ['sync', 'synchronize', 'synchronous'],
+    ['repo', 'repository'],
+    ['impl', 'implementation'],
+    ['util', 'utility', 'helper'],
+    ['param', 'parameter', 'argument'],
+    ['fn', 'func', 'function'],
+    ['btn', 'button'],
+    ['calc', 'calculate', 'calculation'],
+    ['gen', 'generate', 'generator'],
+    ['val', 'validate', 'validation'],
+    ['del', 'delete', 'remove'],
+    ['dir', 'directory', 'folder'],
+    ['env', 'environment'],
+    ['doc', 'document', 'documentation'],
+    ['id', 'identifier'],
+    ['num', 'number'],
+    ['str', 'string'],
+  ];
+
+  // The weight applied to an expanded (synonym) query term, so an exact match on
+  // the literal query token always outranks a synonym-only match.
+  const EXPANSION_WEIGHT = 0.15;
+
+  // Build a stemmed lookup: stem(member) → Set of the group's other stemmed members.
+  const EXPANSIONS = (() => {
+    const map = new Map();
+    for (const group of EXPANSION_GROUPS) {
+      const stemmed = [...new Set(group.map((w) => tokenize(w).join('')).filter(Boolean))];
+      for (const s of stemmed) {
+        if (!map.has(s)) map.set(s, new Set());
+        for (const other of stemmed) if (other !== s) map.get(s).add(other);
+      }
+    }
+    return map;
+  })();
+
+  /**
+   * Expand stemmed query tokens with curated synonyms. Returns a Map of
+   * token → weight (1 for the original query tokens, EXPANSION_WEIGHT for
+   * synonyms). Original tokens always keep full weight even if also a synonym.
+   *
+   * @param {string[]} qToks  stemmed, de-duplicated query tokens
+   * @returns {Map<string, number>}
+   */
+  function expandQuery(qToks) {
+    const weights = new Map();
+    for (const t of qToks) weights.set(t, 1);
+    for (const t of qToks) {
+      const syns = EXPANSIONS.get(t);
+      if (!syns) continue;
+      for (const s of syns) if (!weights.has(s)) weights.set(s, EXPANSION_WEIGHT);
+    }
+    return weights;
+  }
+
   /**
    * BM25 re-rank of candidates against a query. Each candidate is
    * `{ file, sigs }`; the returned objects preserve all original candidate
@@ -13958,23 +14030,24 @@ __factories["./src/retrieval/bm25"] = function(module, exports) {
     }
 
     const qToks = [...new Set(tokenize(query))];
+    const qWeights = expandQuery(qToks); // token → weight (1 exact, <1 synonym)
 
     return docs
       .map((d) => {
         let score = 0;
-        for (const t of qToks) {
+        for (const [t, w] of qWeights) {
           const f = d.tf.get(t);
           if (!f) continue;
           const dfT = df.get(t);
           const idf = Math.log(1 + (N - dfT + 0.5) / (dfT + 0.5));
-          score += (idf * (f * (k1 + 1))) / (f + k1 * (1 - b + (b * d.len) / avgdl));
+          score += w * ((idf * (f * (k1 + 1))) / (f + k1 * (1 - b + (b * d.len) / avgdl)));
         }
         return Object.assign({}, d.cand, { score });
       })
       .sort((a, c) => c.score - a.score || String(a.file).localeCompare(String(c.file)));
   }
 
-  module.exports = { tokenize, stem, bm25rank, PATH_BOOST, STOP };
+  module.exports = { tokenize, stem, bm25rank, PATH_BOOST, STOP, expandQuery, EXPANSIONS, EXPANSION_WEIGHT };
   
 };
 
@@ -17574,7 +17647,7 @@ function __tryGit(args, opts = {}) {
   catch (_) { return ''; }
 }
 
-const VERSION = '8.4.0';
+const VERSION = '8.5.0';
 const MARKER = '\n\n## Auto-generated signatures\n<!-- Updated by gen-context.js -->\n';
 
 function requireSourceOrBundled(key) {

package/llms-full.txt

@@ -11,13 +11,13 @@ ranking keeps the relevant context in scope (cutting tokens ~97% as a side
 effect), with no LLM calls, embeddings, or vector database. Works with Claude,
 Cursor, GitHub Copilot, Aider, Windsurf, local LLMs, and MCP.
 
-# Version: 8.4.0 | Benchmark: sigmap-v8.4-main (2026-07-04)
+# Version: 8.5.0 | Benchmark: sigmap-v8.5-main (2026-07-04)
 # Source: auto-generated from package.json, version.json, benchmarks/latest.json, src/mcp/tools.js, src/config/defaults.js
 # Regenerate: npm run generate:llms   |   Validate: npm run validate:llms
 
 ---
 
-## Core metrics (benchmark: sigmap-v8.4-main, 2026-07-04)
+## Core metrics (benchmark: sigmap-v8.5-main, 2026-07-04)
 
 | Metric | Without SigMap | With SigMap |
 |--------|----------------|-------------|

package/llms.txt

@@ -11,7 +11,7 @@ ranking keeps the relevant context in scope (cutting tokens ~97% as a side
 effect), with no LLM calls, embeddings, or vector database. Works with Claude,
 Cursor, GitHub Copilot, Aider, Windsurf, local LLMs, and MCP.
 
-# Version: 8.4.0 | Benchmark: sigmap-v8.4-main (2026-07-04)
+# Version: 8.5.0 | Benchmark: sigmap-v8.5-main (2026-07-04)
 # Source: auto-generated from package.json, version.json, benchmarks/latest.json, src/mcp/tools.js, src/config/defaults.js
 # Regenerate: npm run generate:llms   |   Validate: npm run validate:llms
 
@@ -23,7 +23,7 @@ Cursor, GitHub Copilot, Aider, Windsurf, local LLMs, and MCP.
 - No blast-radius awareness before editing a hub file — `--impact` shows every file a change touches.
 - Pasted stack traces, CI logs, and JSON bloat the prompt — `squeeze` minimizes them and enriches the top frame from the symbol index.
 
-## Core metrics (benchmark: sigmap-v8.4-main, 2026-07-04)
+## Core metrics (benchmark: sigmap-v8.5-main, 2026-07-04)
 
 - hit@5 retrieval: 86.7% vs 13.6% random baseline (6.4× lift)
 - Token reduction: 97.0% average across benchmark repos

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sigmap",
-  "version": "8.4.0",
+  "version": "8.5.0",
   "description": "97% token reduction for AI coding. Extracts function & class signatures with TF-IDF ranking to feed only the right files to Claude, Cursor, Copilot, Aider, Windsurf, local LLMs & MCP. Zero dependencies, runs offline via npx.",
   "main": "packages/core/index.js",
   "exports": {

package/packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sigmap-cli",
-  "version": "8.4.0",
+  "version": "8.5.0",
   "description": "SigMap CLI wrapper — thin adapter for programmatic CLI invocation",
   "main": "index.js",
   "keywords": [

package/packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sigmap-core",
-  "version": "8.4.0",
+  "version": "8.5.0",
   "description": "SigMap core library — zero-dependency code signature extraction, retrieval, and security scanning",
   "main": "index.js",
   "keywords": [

package/src/mcp/server.js

@@ -18,7 +18,7 @@ const { readContext, searchSignatures, getMap, createCheckpoint, getRouting, exp
 
 const SERVER_INFO = {
   name: 'sigmap',
-  version: '8.4.0',
+  version: '8.5.0',
   description: 'SigMap MCP server — code signatures on demand',
 };
 

package/src/retrieval/bm25.js

@@ -68,6 +68,78 @@ function tokenize(text) {
 // are counted PATH_BOOST times when building the document term-frequency map.
 const PATH_BOOST = 3;
 
+// Curated, high-precision code-domain synonym / abbreviation expansions. A query
+// for `authentication` should still surface a file whose signatures only say
+// `auth`. Kept deliberately tight — over-broad synonyms hurt precision. Groups
+// are expanded bidirectionally (every member maps to the others). Values are
+// tokenized+stemmed at load, so entries are written in natural form.
+const EXPANSION_GROUPS = [
+  ['auth', 'authenticate', 'authentication', 'login', 'signin', 'credential'],
+  ['authorize', 'authorization', 'permission', 'access'],
+  ['config', 'configuration', 'settings', 'options'],
+  ['db', 'database'],
+  ['ctx', 'context'],
+  ['req', 'request'],
+  ['res', 'response'],
+  ['err', 'error'],
+  ['msg', 'message'],
+  ['init', 'initialize', 'initialization', 'setup'],
+  ['async', 'asynchronous'],
+  ['sync', 'synchronize', 'synchronous'],
+  ['repo', 'repository'],
+  ['impl', 'implementation'],
+  ['util', 'utility', 'helper'],
+  ['param', 'parameter', 'argument'],
+  ['fn', 'func', 'function'],
+  ['btn', 'button'],
+  ['calc', 'calculate', 'calculation'],
+  ['gen', 'generate', 'generator'],
+  ['val', 'validate', 'validation'],
+  ['del', 'delete', 'remove'],
+  ['dir', 'directory', 'folder'],
+  ['env', 'environment'],
+  ['doc', 'document', 'documentation'],
+  ['id', 'identifier'],
+  ['num', 'number'],
+  ['str', 'string'],
+];
+
+// The weight applied to an expanded (synonym) query term, so an exact match on
+// the literal query token always outranks a synonym-only match.
+const EXPANSION_WEIGHT = 0.15;
+
+// Build a stemmed lookup: stem(member) → Set of the group's other stemmed members.
+const EXPANSIONS = (() => {
+  const map = new Map();
+  for (const group of EXPANSION_GROUPS) {
+    const stemmed = [...new Set(group.map((w) => tokenize(w).join('')).filter(Boolean))];
+    for (const s of stemmed) {
+      if (!map.has(s)) map.set(s, new Set());
+      for (const other of stemmed) if (other !== s) map.get(s).add(other);
+    }
+  }
+  return map;
+})();
+
+/**
+ * Expand stemmed query tokens with curated synonyms. Returns a Map of
+ * token → weight (1 for the original query tokens, EXPANSION_WEIGHT for
+ * synonyms). Original tokens always keep full weight even if also a synonym.
+ *
+ * @param {string[]} qToks  stemmed, de-duplicated query tokens
+ * @returns {Map<string, number>}
+ */
+function expandQuery(qToks) {
+  const weights = new Map();
+  for (const t of qToks) weights.set(t, 1);
+  for (const t of qToks) {
+    const syns = EXPANSIONS.get(t);
+    if (!syns) continue;
+    for (const s of syns) if (!weights.has(s)) weights.set(s, EXPANSION_WEIGHT);
+  }
+  return weights;
+}
+
 /**
  * BM25 re-rank of candidates against a query. Each candidate is
  * `{ file, sigs }`; the returned objects preserve all original candidate
@@ -103,20 +175,21 @@ function bm25rank(query, candidates) {
   }
 
   const qToks = [...new Set(tokenize(query))];
+  const qWeights = expandQuery(qToks); // token → weight (1 exact, <1 synonym)
 
   return docs
     .map((d) => {
       let score = 0;
-      for (const t of qToks) {
+      for (const [t, w] of qWeights) {
         const f = d.tf.get(t);
         if (!f) continue;
         const dfT = df.get(t);
         const idf = Math.log(1 + (N - dfT + 0.5) / (dfT + 0.5));
-        score += (idf * (f * (k1 + 1))) / (f + k1 * (1 - b + (b * d.len) / avgdl));
+        score += w * ((idf * (f * (k1 + 1))) / (f + k1 * (1 - b + (b * d.len) / avgdl)));
       }
       return Object.assign({}, d.cand, { score });
     })
     .sort((a, c) => c.score - a.score || String(a.file).localeCompare(String(c.file)));
 }
 
-module.exports = { tokenize, stem, bm25rank, PATH_BOOST, STOP };
+module.exports = { tokenize, stem, bm25rank, PATH_BOOST, STOP, expandQuery, EXPANSIONS, EXPANSION_WEIGHT };