robot_lab-document_store 0.2.7 → 0.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: ba7995bd1cc8a7136598de913b944988b3e96b12a7717df76321ec92c587fe90
-  data.tar.gz: 9837c42e6cf67050c3e15b8e5631c053e094253ceaea5012096ad2c9b9b5bec9
+  metadata.gz: 28fc49eabc0cc41a494dd3616b80aae598d136ed9ac43701901c1febea570f12
+  data.tar.gz: cd3ab07965633d3a7becd7d0c70c668f17b6b5dcb19e0af02cafc82fee5ca6a0
 SHA512:
-  metadata.gz: 6a6c101a2a02ca3d8555d11d9b02e6b763d6ed33cf7ad927fad8bb574809d481772591a08023f60569b85e7f03a1edaf31273dd1cc44cab95c2c3a4b23892165
-  data.tar.gz: 6bb3eefc700cffff70ed42bdddf5d588959a7291bd8346a8a16c7475c413b9977e0f8bc46635a782e7166896ab5103d7f8859fbb13897a86b8e506ec7a41e86c
+  metadata.gz: 36fba6cb5abe124767d1f31f0e5f4a411c6a9c2a65ebaf56b3198de271c1be7c61569b0238729a79d1b2c979982af2dd12ca0ca856a7d9274cb99cc73225757e
+  data.tar.gz: c39107b2526d209f8a793ecf7d7a77bff3c31dbc8ceef9de79c05e2ce3df65dad0cf0839803e270d5d04a2162d7bfbc1ace853f084acc854b0098cbc8340792a

data/.envrc

@@ -1,3 +1,6 @@
+# robot_lab_project/robot_lab-document_store/.envrc
+
 source_up
+
 export RR=`pwd`
 export BUNDLE_GEMFILE=Gemfile

data/CHANGELOG.md

@@ -1,5 +1,9 @@
 ## [Unreleased]
 
+## [0.2.8] - 2026-09-09
+
+Released in lockstep with `robot_lab` core v0.2.8: this gem now resolves the released core gem from RubyGems instead of the local sibling checkout (local-path development remains available via `BUNDLE_GEMFILE=Gemfile.local`). Also in this release: `cosine_similarity` split during the reek pass (remaining sites annotated), and gem lifecycle tasks moved to asgard.
+
 ### Added
 - `.loki` Asgard task file: `test`, `rubocop`, `rubocop_fix`, `flog`, `flay`, `quality`, `build`, `install`, `release`, and `console` tasks via the Asgard task runner
 - `flay_check` Rake task: structural code duplication gate (mass threshold 50); integrated into the `quality` Rake task

data/Rakefile

@@ -1,6 +1,5 @@
 # frozen_string_literal: true
 
-require 'bundler/gem_tasks'
 require 'rake/testtask'
 
 Rake::TestTask.new(:test) do |t|

data/_typos.toml

@@ -0,0 +1,9 @@
+# False-positive suppressions for the typos quality gate (asgard).
+# Everything here was reviewed by hand — see git history for context.
+
+[default.extend-identifiers]
+# The Porter-style stemmer strips suffixes and its docs show raw stem
+# output; these are deliberate word fragments, not typos.
+ment     = "ment"      # the -ment suffix (stemmer regex + docs table)
+activiti = "activiti"  # stem of "activities" (docs table)
+runn     = "runn"      # stem of "running" (docs table)

data/lib/robot_lab/document_store/version.rb

@@ -2,6 +2,6 @@
 
 module RobotLab
   class DocumentStore
-    VERSION = '0.2.7'
+    VERSION = '0.2.8'
   end
 end

data/lib/robot_lab/document_store.rb

@@ -29,6 +29,7 @@ module RobotLab
   #   memory.store_document(:readme, File.read("README.md"))
   #   memory.search_documents("how to configure redis", limit: 3)
   #
+  # :reek:RepeatedConditional -- @using_fastembed selects the dense vs sparse embedding path, fixed at construction.
   class DocumentStore
     # @api private
     FASTEMBED_AVAILABLE = begin
@@ -72,6 +73,7 @@ module RobotLab
     # @param limit [Integer] maximum number of results (default 5)
     # @return [Array<Hash>] results sorted by score descending.
     #   Each hash contains +:key+, +:text+, and +:score+ (Float 0.0..1.0).
+    # :reek:TooManyStatements -- linear embed/score/sort pipeline; the mutex block inflates the count.
     def search(query, limit: 5)
       return [] if empty?
 
@@ -155,32 +157,37 @@ module RobotLab
     def cosine_similarity(vec_a, vec_b)
       return 0.0 unless vec_a && vec_b
 
-      if @using_fastembed
-        return 0.0 if vec_a.empty? || vec_b.empty?
-        return 0.0 if vec_a.length != vec_b.length
-
-        dot    = 0.0
-        norm_a = 0.0
-        norm_b = 0.0
-
-        vec_a.each_with_index do |a, i|
-          b       = vec_b[i]
-          dot    += a * b
-          norm_a += a * a
-          norm_b += b * b
-        end
+      @using_fastembed ? dense_cosine(vec_a, vec_b) : sparse_cosine(vec_a, vec_b)
+    end
 
-        return 0.0 if norm_a.zero? || norm_b.zero?
+    # :reek:FeatureEnvy -- pure vector math over its two arguments; there is no better home than the store that owns both paths.
+    # :reek:TooManyStatements -- one guarded dot-product/norm accumulation; splitting the loop would obscure the formula.
+    def dense_cosine(vec_a, vec_b)
+      return 0.0 if vec_a.empty? || vec_b.empty?
+      return 0.0 if vec_a.length != vec_b.length
 
-        dot / (Math.sqrt(norm_a) * Math.sqrt(norm_b))
-      else
-        sparse_cosine(vec_a, vec_b)
+      dot    = 0.0
+      norm_a = 0.0
+      norm_b = 0.0
+
+      vec_a.each_with_index do |a, i|
+        b       = vec_b[i]
+        dot    += a * b
+        norm_a += a * a
+        norm_b += b * b
       end
+
+      return 0.0 if norm_a.zero? || norm_b.zero?
+
+      dot / (Math.sqrt(norm_a) * Math.sqrt(norm_b))
     end
 
     # ── Fallback TF-IDF word-frequency path ─────────────────────────────────
 
     # Returns a sparse Hash{String => Float} L2-normalised term-frequency vector.
+    # :reek:FeatureEnvy -- builds and normalises the local counts hash it returns; there is no other object involved.
+    # :reek:TooManyStatements -- one count-then-normalise sequence over the local hash.
+    # :reek:UncommunicativeVariableName -- single-char block param (w = word) is accepted project convention.
     def fallback_vector(text)
       counts = Hash.new(0)
       text.downcase.scan(/[a-z]+/).each do |w|
@@ -195,6 +202,7 @@ module RobotLab
       counts.transform_values { |c| c / norm }
     end
 
+    # :reek:TooManyStatements -- one guarded dot-product/norm accumulation; splitting the loop would obscure the formula.
     def sparse_cosine(vec_a, vec_b)
       return 0.0 if vec_a.empty? || vec_b.empty?
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: robot_lab-document_store
 version: !ruby/object:Gem::Version
-  version: 0.2.7
+  version: 0.2.8
 platform: ruby
 authors:
 - Dewayne VanHoozer
@@ -58,6 +58,7 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- _typos.toml
 - docs/api_reference.md
 - docs/assets/architecture.svg
 - docs/getting_started.md
@@ -96,7 +97,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 4.0.19
+rubygems_version: 4.0.20
 specification_version: 4
 summary: Embedding-based semantic document store for RobotLab agents
 test_files: []