rubric_llm 0.8.0 → 0.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: fe5f964e023687c815cf95b56673d05f3103f15a679ebb6f5d272d287c396163
-  data.tar.gz: f082d306d7e50347dc6a53caf453dc7e24abbd0213012711506692516ff38a47
+  metadata.gz: 73d2f6cf20d68d6f47f15d8f92e9ff7ce8efcd2890bec070037f76879dc022c5
+  data.tar.gz: 0d59825beab623fc60f8a4c62a132bce8ab1b6b940364a58f02234bb08e2c546
 SHA512:
-  metadata.gz: 8cdba0f5196529eed16d2c19edaca418f8feedca62244724a206e6b4baa1ab9ef13660a3cf24f1711ad52e43856f325648b88ee8443da0cce7bee9a9f9b637d7
-  data.tar.gz: c2828756fca3eb3395567bd61ebac9b80bdffd12dbdd4b410f000b5001b68169be14101a95bde4c0541f98526c9bdc7ff665e22e2d918fda75072af4dd1e4dc2
+  metadata.gz: 8d0e52051db16a2b845fb865d6ab88e43521165752937df2eeb6823dc62e8e0e860516e2d2d2c85f9ff37c414268ac8720516cb2dd9db2dd5911a97577b22552
+  data.tar.gz: 3b904616349d102198a71be1188766aedb8c80adce7e8ac45e8ed616f02c0a921bd5c02980a6f49fc37aa12a6819d4acb019db9c557701b8f413980a34c6fa0b

data/CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.9.0] - 2026-10-14
+
+### Changed
+
+- Require RubyLLM `~> 2.1`, `>= 2.1.1` (>= 2.1.1, < 3.0), excluding 2.1.0's fresh-install Faraday dependency resolution defect; Ruby >= 3.4 remains supported
+- Verify RubyLLM 2.1's shared transport connections with offline real-client contracts: outer judge retries retain their HTTP attempt budgets, while independent judge requests keep credentials and conversation history separate
+
 ## [0.8.0] - 2026-09-22
 
 ### Changed

data/README.md

@@ -8,15 +8,15 @@ Lightweight LLM evaluation framework for Ruby, inspired by [DeepEval](https://gi
 
 Provider-agnostic evaluation with pluggable metrics, statistical A/B comparison, and test framework integration: no Rails, no ActiveRecord, no UI. Works anywhere Ruby runs.
 
-RubricLLM `0.7.0` supports RubyLLM `~> 2.0` and Ruby 3.4 or later. Applications that use RubyLLM 1.x should stay on RubricLLM `0.5.x`.
+RubricLLM 0.9.0 requires RubyLLM `~> 2.1`, `>= 2.1.1` (>= 2.1.1, < 3.0) and Ruby 3.4 or later. Applications that use RubyLLM 1.x should stay on RubricLLM `0.5.x`.
 
 ## Installation
 
 Update both gem constraints together:
 
 ```ruby
-gem "rubric_llm", "~> 0.7.0"
-gem "ruby_llm", "~> 2.0"
+gem "rubric_llm", "~> 0.9.0"
+gem "ruby_llm", "~> 2.1", ">= 2.1.1"
 ```
 
 Then resolve both gems together:
@@ -25,12 +25,14 @@ Then resolve both gems together:
 bundle update rubric_llm ruby_llm
 ```
 
-If the application still has a RubyLLM 1.x constraint, update both constraints before running Bundler.
+If the application still has a RubyLLM 1.x constraint, update both constraints before running Bundler. RubyLLM 2.1.1 or later is required: it fixes a fresh-install Faraday dependency resolution problem in 2.1.0.
+
+RubyLLM 2.1's `RubyLLM::Judge` and `RubyLLM::Evaluation` are separate upstream APIs. RubricLLM keeps its own judge, metrics, and reports; this upgrade does not switch evaluation engines.
 
 Or install directly:
 
 ```bash
-gem install rubric_llm --version 0.7.0
+gem install rubric_llm --version 0.9.0
 ```
 
 ## Quick Start
@@ -90,7 +92,7 @@ RubyLLM.configure do |config|
 end
 ```
 
-Structured output support depends on the selected provider and model. RubricLLM sends its schema when RubyLLM reports structured output support. Otherwise it requests JSON text and validates the response object and score locally. Check the target provider's support before relying on a schema or a specific protocol. See RubyLLM's [2.0 upgrade guide](https://rubyllm.com/next/upgrading/), [request control guide](https://rubyllm.com/next/chat-request-control/), and [structured output support](https://rubyllm.com/next/structured-output/).
+Structured output support depends on the selected provider and model. RubricLLM sends its schema when RubyLLM reports structured output support. Otherwise it requests JSON text and validates the response object and score locally. Check the target provider's support before relying on a schema or a specific protocol. See RubyLLM's [upgrade guide](https://rubyllm.com/upgrading/), [request control guide](https://rubyllm.com/chat-request-control/), and [structured output support](https://rubyllm.com/structured-output/).
 
 ### Judge Thinking Effort
 
@@ -153,11 +155,11 @@ RubricLLM.configure do |c|
 end
 ```
 
-RubricLLM has no Rails models or database migrations. If the application also uses RubyLLM's Rails persistence, follow RubyLLM's 2.0 upgrade guide and run its phased migrations separately.
+RubricLLM has no Rails models or database migrations. If the application also uses RubyLLM's Rails persistence, follow RubyLLM's [upgrade guide](https://rubyllm.com/upgrading/) and run its migrations separately.
 
 ### Retries
 
-RubyLLM transport retries and RubricLLM judge retries remain separate. With RubyLLM's default `config.max_retries = 3` and RubricLLM's default `max_retries: 2`, one retryable metric failure can produce up to `(3 + 1) * (2 + 1) = 12` HTTP attempts. Set `RUBRIC_MAX_RETRIES` and `RUBRIC_RETRY_BASE_DELAY` for RubricLLM's layer, and set RubyLLM's `config.max_retries` and related transport settings for its layer. RubricLLM 0.6 does not combine or redesign these retry layers.
+RubyLLM transport retries and RubricLLM judge retries remain separate. With RubyLLM's default `config.max_retries = 3` and RubricLLM's default `max_retries: 2`, one retryable metric failure can produce up to `(3 + 1) * (2 + 1) = 12` HTTP attempts. Set `RUBRIC_MAX_RETRIES` and `RUBRIC_RETRY_BASE_DELAY` for RubricLLM's layer, and set RubyLLM's `config.max_retries` and related transport settings for its layer. RubricLLM does not combine or redesign these retry layers. RubyLLM 2.1 reuses transport connections for matching settings, including across RubricLLM's outer retries; this does not change the HTTP attempt budgets or share judge conversation history.
 
 RubyLLM classifies OpenAI's HTTP 429 `insufficient_quota` response as a rate-limit error, so an exhausted account uses both retry budgets and their delays before the error is returned.
 
@@ -426,7 +428,7 @@ Deep dives live in the [project wiki](https://github.com/dpaluy/rubric_llm/wiki)
 ## Requirements
 
 - Ruby >= 3.4
-- [ruby_llm](https://github.com/crmne/ruby_llm) ~> 2.0 for RubricLLM 0.7.0
+- [ruby_llm](https://github.com/crmne/ruby_llm) >= 2.1.1, < 3.0 for the current development version
 - An API key for your chosen LLM provider (set via RubyLLM configuration)
 
 ## Contributing

data/lib/rubric_llm/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module RubricLLM
-  VERSION = "0.8.0"
+  VERSION = "0.9.0"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rubric_llm
 version: !ruby/object:Gem::Version
-  version: 0.8.0
+  version: 0.9.0
 platform: ruby
 authors:
 - David Paluy
@@ -29,14 +29,20 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '2.1'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.1.1
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '2.0'
+        version: '2.1'
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 2.1.1
 description: Provider-agnostic LLM evaluation with pluggable metrics, statistical
   A/B comparison, and test framework integration. Ragas for Ruby, powered by RubyLLM.
 email: