sigmap 2.6.0 → 2.7.0

package/CHANGELOG.md

@@ -6,7 +6,43 @@ Format: [Semantic Versioning](https://semver.org/)
 
 ---
 
-## [2.6.0] — upcoming · [#16](https://github.com/manojmallick/sigmap/issues/16) · branch: `feat/v2.6-research-mode`
+## [2.7.0] — upcoming · [#19](https://github.com/manojmallick/sigmap/issues/19) · branch: `feat/v2.7-ranking-optimization`
+
+### Planned additions
+- **Fine-tuned ranking weights** — optimize `exactToken`, `symbolMatch`, `prefixMatch`, `pathMatch`, and `recencyBoost` weights in `src/retrieval/ranker.js` based on benchmark-driven evaluation
+- **TF-IDF scoring option** — add TF-IDF (term frequency-inverse document frequency) as an alternative scoring method for better semantic relevance in large codebases
+- **Configurable weight presets** — `precision`, `balanced`, `recall` presets for different use cases; configurable via `retrieval.preset` in config
+- **`formatRankTable` and `formatRankJSON` improvements** — better output formatting for ranked results with score breakdown and relevance explanation
+- **Performance optimization** — optimize ranking algorithm for large codebases (10K+ files), target <100ms for --query on 1000-file repos
+- **Regression tests** — ensure hit@5 maintains ≥ 0.80 (no regression from v2.6)
+- **Precision improvement** — target precision@5 improvement of ≥ 5% over v2.6
+
+### Config additions
+```json
+{
+  "retrieval": {
+    "topK": 10,
+    "recencyBoost": 1.5,
+    "preset": "balanced",
+    "weights": {
+      "exactToken": 1.0,
+      "symbolMatch": 0.5,
+      "prefixMatch": 0.3,
+      "pathMatch": 0.8
+    }
+  }
+}
+```
+
+### Go / No-go criteria
+- All tests green (21 extractor + all integration suites)
+- Benchmark hit@5 ≥ 0.80 (no regression from v2.6)
+- Precision@5 improves by ≥ 5%
+- `--query` performance <100ms for 1000-file repos
+
+---
+
+## [2.6.0] — 2026-04-05 · [#16](https://github.com/manojmallick/sigmap/issues/16)
 
 ### Planned additions
 - **`benchmarks/repos/`** — register 5 real open-source repos (express, flask, gin, spring-petclinic, rails) as git submodules or clone targets for evaluation

package/README.md

@@ -86,28 +86,6 @@ AI agent session starts with full context
 
 ---
 
-## 🔭 What's next — v2.5-v2.6 (in progress · [#14](https://github.com/manojmallick/sigmap/issues/14) · [#16](https://github.com/manojmallick/sigmap/issues/16))
-
-### v2.5 — Impact Layer
-
-| Feature | Description |
-|---|---|
-| **`--impact <file>`** | Show every file that transitively depends on a changed file — instant blast-radius awareness |
-| **`--impact --json`** | Machine-readable output for CI pipelines |
-| **`get_impact` MCP tool** | 9th MCP tool — `{ file, depth? }` → impacted files + signatures |
-| **`src/map/dep-graph.js`** | Reverse-dependency graph built from the import analysis; circular deps handled safely |
-| **15 new tests** | `impact.test.js` — direct deps, transitive deps, depth limit, JSON output |
-
-### v2.6 — Research Mode
-
-| Feature | Description |
-|---|---|
-| **`--benchmark --repo <path>`** | Run benchmarks against any external repository (express, flask, gin, spring-petclinic, rails) |
-| **`--report --paper`** | Generate paper-ready metrics: markdown + LaTeX tables for academic publishing |
-| **50 real eval tasks** | JSONL task file covering 5 real open-source repos — `benchmarks/tasks/retrieval-real.jsonl` |
-| **`src/eval/paper.js`** | Zero-dependency LaTeX table formatter for token reduction, hit@5, MRR, latency (p50/p95/p99) |
-| **8 new tests** | `paper.test.js` — report generation, LaTeX syntax validation, graceful failures |
-
 ## 🆕 What's new in 2.4
 
 | Feature | Description |
@@ -132,6 +110,25 @@ AI agent session starts with full context
 
 ---
 
+## 🔭 What's next — v2.7 (in progress · [#19](https://github.com/manojmallick/sigmap/issues/19))
+
+### v2.7 — Ranking Optimization
+
+| Feature | Description |
+|---|---|
+| **Fine-tuned ranking weights** | Optimize weights in `src/retrieval/ranker.js` for better precision based on benchmark evaluation |
+| **TF-IDF scoring** | Add term frequency-inverse document frequency scoring option for better semantic relevance |
+| **Weight presets** | `precision`, `balanced`, `recall` presets — configurable via `retrieval.preset` |
+| **Performance optimization** | <100ms query performance for 1000-file repos, optimized for large codebases (10K+ files) |
+| **Precision improvement** | Target ≥5% precision@5 improvement while maintaining hit@5 ≥ 0.80 |
+
+---
+| **`get_impact` MCP tool** | 9th MCP tool — `{ file, depth? }` → impacted files + signatures |
+| **`src/map/dep-graph.js`** | Reverse-dependency graph built from the import analysis; circular deps handled safely |
+| **15 new tests** | `impact.test.js` — direct deps, transitive deps, depth limit, JSON output |
+
+---
+
 ## 🚀 Quick start
 
 **No install required — just Node.js 18+.**

package/gen-context.js

@@ -4304,7 +4304,7 @@ const path = require('path');
 const os = require('os');
 const { execSync } = require('child_process');
 
-const VERSION = '2.6.0';
+const VERSION = '2.7.0';
 const MARKER = '\n\n## Auto-generated signatures\n<!-- Updated by gen-context.js -->\n';
 
 function requireSourceOrBundled(key) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sigmap",
-  "version": "2.6.0",
+  "version": "2.7.0",
   "description": "Zero-dependency AI context engine — 97% token reduction. No npm install. Runs on Node 18+.",
   "main": "gen-context.js",
   "exports": {

package/packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sigmap-cli",
-  "version": "2.6.0",
+  "version": "2.7.0",
   "description": "SigMap CLI wrapper — thin adapter for programmatic CLI invocation",
   "main": "index.js",
   "keywords": [

package/packages/core/README.md

@@ -128,11 +128,9 @@ const health = score('/path/to/project');
 
 All existing CLI flags (`--generate`, `--watch`, `--mcp`, `--query`, `--analyze`, `--benchmark`, `--health`, …) are unchanged.
 
-## What's next — v2.5-v2.6
+## What's next — v2.7
 
-v2.5 adds `analyzeImpact(changedFiles, cwd)` to `packages/core` — given a list of changed files, it returns every file that transitively imports them. See [issue #14](https://github.com/manojmallick/sigmap/issues/14).
-
-v2.6 adds benchmark and paper reporting capabilities — run evaluations against external repos and export metrics in LaTeX format for academic papers. See [issue #16](https://github.com/manojmallick/sigmap/issues/16).
+v2.7 adds ranking optimization and fine-tuned weights for better precision in query-aware retrieval. TF-IDF scoring option, configurable weight presets (precision, balanced, recall), and performance optimization for large codebases. See [issue #19](https://github.com/manojmallick/sigmap/issues/19).
 
 See the full [roadmap](https://manojmallick.github.io/sigmap/roadmap.html).
 

package/packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "sigmap-core",
-  "version": "2.6.0",
+  "version": "2.7.0",
   "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: '2.6.0',
+  version: '2.7.0',
   description: 'SigMap MCP server — code signatures on demand',
 };