ruby_llm-contract 0.4.0 → 0.4.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/CHANGELOG.md +6 -0
- data/Gemfile.lock +2 -2
- data/README.md +22 -0
- data/lib/ruby_llm/contract/rake_task.rb +1 -1
- data/lib/ruby_llm/contract/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: f8cbf4696de5e80a05baefbeda7e91e7afc322ead379e52da1e0457fae3a8ca2
|
|
4
|
+
data.tar.gz: 67bd866954f134939d0fa87222212bd665a9d1e2ba0e3248a061f55b67ad72c8
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: c4efd526237cd354739f4868cbe020211aa27878d9dd590c828d5e7a18d613a62664bf839f51e704917a94926c55e0546938316fa3ff6367cfdb5d06263443ad
|
|
7
|
+
data.tar.gz: 0ba0ac4f55716b360f0702d137fbdc48edfc2e9fba8c4e04d5adbe45ef561c4b1cd65c14793e1b868b3716e7417bdfdb9bb67eef2ab4f3ca69c74a4b3e911844
|
data/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,11 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## 0.4.1 (2026-03-24)
|
|
4
|
+
|
|
5
|
+
- **RakeTask `:environment` fix** — uses `defined?(::Rails)` instead of `Rake::Task.task_defined?(:environment)`. Works in Rails 8 without manual `Rake::Task.enhance`.
|
|
6
|
+
- **Concurrent eval deterministic** — `clone_for_concurrency` protocol, `ContextHelpers` extracted.
|
|
7
|
+
- **README** — added eval history, concurrency, quality tracking examples.
|
|
8
|
+
|
|
3
9
|
## 0.4.0 (2026-03-24)
|
|
4
10
|
|
|
5
11
|
Observability & Scale — see what changed, run it fast, debug it easily.
|
data/Gemfile.lock
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
PATH
|
|
2
2
|
remote: .
|
|
3
3
|
specs:
|
|
4
|
-
ruby_llm-contract (0.4.
|
|
4
|
+
ruby_llm-contract (0.4.1)
|
|
5
5
|
dry-types (~> 1.7)
|
|
6
6
|
ruby_llm (~> 1.0)
|
|
7
7
|
ruby_llm-schema (~> 0.3)
|
|
@@ -165,7 +165,7 @@ CHECKSUMS
|
|
|
165
165
|
rubocop-ast (1.49.1) sha256=4412f3ee70f6fe4546cc489548e0f6fcf76cafcfa80fa03af67098ffed755035
|
|
166
166
|
ruby-progressbar (1.13.0) sha256=80fc9c47a9b640d6834e0dc7b3c94c9df37f08cb072b7761e4a71e22cff29b33
|
|
167
167
|
ruby_llm (1.14.0) sha256=57c6f7034fc4a44504ea137d70f853b07824f1c1cdbe774ab3ab3522e7098deb
|
|
168
|
-
ruby_llm-contract (0.4.
|
|
168
|
+
ruby_llm-contract (0.4.1)
|
|
169
169
|
ruby_llm-schema (0.3.0) sha256=a591edc5ca1b7f0304f0e2261de61ba4b3bea17be09f5cf7558153adfda3dec6
|
|
170
170
|
unicode-display_width (3.2.0) sha256=0cdd96b5681a5949cdbc2c55e7b420facae74c4aaf9a9815eee1087cb1853c42
|
|
171
171
|
unicode-emoji (4.2.0) sha256=519e69150f75652e40bf736106cfbc8f0f73aa3fb6a65afe62fefa7f80b0f80f
|
data/README.md
CHANGED
|
@@ -135,6 +135,28 @@ expect(ClassifyTicket).to pass_eval("regression")
|
|
|
135
135
|
.without_regressions
|
|
136
136
|
```
|
|
137
137
|
|
|
138
|
+
## Track quality over time
|
|
139
|
+
|
|
140
|
+
```ruby
|
|
141
|
+
# Save every eval run
|
|
142
|
+
report = ClassifyTicket.run_eval("regression", context: { model: "gpt-4.1-nano" })
|
|
143
|
+
report.save_history!(model: "gpt-4.1-nano")
|
|
144
|
+
|
|
145
|
+
# View trend
|
|
146
|
+
history = report.eval_history(model: "gpt-4.1-nano")
|
|
147
|
+
history.score_trend # => :stable_or_improving | :declining
|
|
148
|
+
history.drift? # => true (score dropped > 10%)
|
|
149
|
+
```
|
|
150
|
+
|
|
151
|
+
## Run evals fast
|
|
152
|
+
|
|
153
|
+
```ruby
|
|
154
|
+
# 4x faster with parallel execution
|
|
155
|
+
report = ClassifyTicket.run_eval("regression",
|
|
156
|
+
context: { model: "gpt-4.1-nano" },
|
|
157
|
+
concurrency: 4)
|
|
158
|
+
```
|
|
159
|
+
|
|
138
160
|
## Predict cost before running
|
|
139
161
|
|
|
140
162
|
```ruby
|