llm_optimizer 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d382e2ae48971edae81c24fa4e05bbacf9394c04dabed28b0277ca429e75a98d
-  data.tar.gz: d807840237cf09e8b271063660242ae1c460b682425a50389c60f396b086e2c4
+  metadata.gz: 6a0351ff5590228acf939201d0c7eee71e33ee39a0cd20df33e76187c827ab34
+  data.tar.gz: 6bc7df5aa71407be80ecd07104e1dbff9a25a9ecab7a95cb390261f97fa212e8
 SHA512:
-  metadata.gz: 8cac9e17c1f243c17d997e799daf25d886b329c09e83c84d9151f55abbb50d36a7e1b486171e401a645443022bb4de05e4430d0e303e05587dd1b244eda18cbe
-  data.tar.gz: 598b000eabc6a4c0000b3b9bd2162231c619d7618653ca6356948b623f0524db048c7b1f9a8a589905c6b611a10fe6bdc42e7490b432fe8f6047b75dcc35038a
+  metadata.gz: e6822ea254300a957c8aa5953d267695ebc2ae4c1e2fa478492d175534bc990eac9bb5bb39127b8418e7306a3f5de9e8124832f9aeac9f723979e92a68babdec
+  data.tar.gz: 4248569dc2a969518142ac2749b6b6e9dc6defedec71e67eeec2480ade3a1aea05261736a2438c994906c05a1d1a1a7991055d48eab9ac0cc33f1344a88a221c

data/CHANGELOG.md

@@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.1.2] - 2026-04-10
+
+### Fixed
+- `SemanticCache` used `pack("f*")` (32-bit) for both the Redis key hash and embedding serialization, causing precision loss on round-trip through MessagePack. Switched to `pack("G*")` / `unpack("G*")` (64-bit IEEE 754) — self-similarity is now exactly `1.0` and cache lookups work correctly with real embedding providers (Voyage AI, OpenAI, Cohere, etc.)
+- `HistoryManager` summarization failed with `ConfigurationError: No llm_caller configured` when invoked through the gateway pipeline. The internal `raw_llm_call` lambda was missing `config: call_config`, so it couldn't resolve the user's configured `llm_caller`
+- Updated `test/unit/test_gateway.rb` mock Redis helper to use `pack("G*")` to match the corrected `SemanticCache` key format
+
+### Added
+- `bin/test_semantic_cache.rb` — runnable smoke test for semantic cache using Voyage AI embeddings + Anthropic Claude
+- `bin/test_history_manager.rb` — runnable smoke test for history manager sliding window using Anthropic Claude
+
 ## [0.1.1] - 2026-04-10
 
 ### Fixed
@@ -46,5 +57,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - `OptimizeResult` struct with `response`, `model`, `model_tier`, `cache_status`, `original_tokens`, `compressed_tokens`, `latency_ms`, `messages`
 - Unit test suite covering all components with positive and negative scenarios using Minitest + Mocha
 
-[Unreleased]: https://github.com/arunkumarry/llm_optimizer/compare/v0.1.0...HEAD
+[Unreleased]: https://github.com/arunkumarry/llm_optimizer/compare/v0.1.2...HEAD
+[0.1.2]: https://github.com/arunkumarry/llm_optimizer/compare/v0.1.1...v0.1.2
+[0.1.1]: https://github.com/arunkumarry/llm_optimizer/compare/v0.1.0...v0.1.1
 [0.1.0]: https://github.com/arunkumarry/llm_optimizer/releases/tag/v0.1.0

data/lib/llm_optimizer/semantic_cache.rb

@@ -15,7 +15,13 @@ module LlmOptimizer
 
     def store(embedding, response)
       key     = cache_key(embedding)
-      payload = MessagePack.pack({ "embedding" => embedding, "response" => response })
+      # Serialize embedding as raw 64-bit big-endian doubles to preserve full
+      # Float precision. MessagePack silently downcasts Ruby Float to 32-bit,
+      # which corrupts cosine similarity on deserialization.
+      payload = MessagePack.pack({
+                                   "embedding" => embedding.pack("G*"), # binary string, lossless
+                                   "response" => response
+                                 })
       @redis.set(key, payload, ex: @ttl)
     rescue ::Redis::BaseError => e
       warn "[llm_optimizer] SemanticCache store failed: #{e.message}"
@@ -33,7 +39,8 @@ module LlmOptimizer
         next unless raw
 
         entry = MessagePack.unpack(raw)
-        stored_embedding = entry["embedding"]
+        # Unpack the binary string back to 64-bit doubles
+        stored_embedding = entry["embedding"].unpack("G*")
         score = cosine_similarity(embedding, stored_embedding)
 
         if score > best_score
@@ -60,7 +67,10 @@ module LlmOptimizer
     private
 
     def cache_key(embedding)
-      KEY_NAMESPACE + Digest::SHA256.hexdigest(embedding.pack("f*"))
+      # Use "G*" (64-bit big-endian double) to match Ruby's native Float precision.
+      # "f*" (32-bit) truncates precision and produces inconsistent hashes for the
+      # same embedding across serialize/deserialize round trips.
+      KEY_NAMESPACE + Digest::SHA256.hexdigest(embedding.pack("G*"))
     end
   end
 end

data/lib/llm_optimizer/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module LlmOptimizer
-  VERSION = "0.1.1"
+  VERSION = "0.1.2"
 end

data/lib/llm_optimizer.rb

@@ -158,7 +158,7 @@ module LlmOptimizer
     # History management
     messages = options[:messages]
     if call_config.manage_history && messages
-      llm_caller = ->(p, model:) { raw_llm_call(p, model: model) }
+      llm_caller = ->(p, model:) { raw_llm_call(p, model: model, config: call_config) }
       history_mgr = HistoryManager.new(
         llm_caller: llm_caller,
         simple_model: call_config.simple_model,

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: llm_optimizer
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - arun kumar
@@ -79,20 +79,6 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '0.65'
-- !ruby/object:Gem::Dependency
-  name: prop_check
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '1.0'
 description: llm_optimizer reduces LLM API costs by up to 80% through semantic caching,
   intelligent model routing, token pruning, and conversation history summarization.
   Strictly opt-in and non-invasive.