lemans 1.3.5 → 1.5.0
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 +21 -0
- data/README.md +17 -2
- data/exe/lemans-remote +141 -3
- data/exe/lemans-viewer +962 -0
- data/lib/lemans/agent.rb +4 -1
- data/lib/lemans/agents/miniswen.rb +10 -5
- data/lib/lemans/agents/miniswen_installed.rb +23 -5
- data/lib/lemans/agents/nop.rb +1 -1
- data/lib/lemans/agents/oracle.rb +1 -1
- data/lib/lemans/agents.rb +4 -2
- data/lib/lemans/cli/templates/bench/bench.yml +7 -0
- data/lib/lemans/cli.rb +85 -31
- data/lib/lemans/config/verifier.rb +10 -2
- data/lib/lemans/environments/docker/proxy/Dockerfile +4 -0
- data/lib/lemans/environments/docker/proxy/README.md +49 -0
- data/lib/lemans/environments/docker/proxy/server.rb +79 -0
- data/lib/lemans/environments/docker.rb +79 -16
- data/lib/lemans/result.rb +52 -1
- data/lib/lemans/runner/task.rb +9 -5
- data/lib/lemans/runner.rb +45 -2
- data/lib/lemans/store.rb +6 -0
- data/lib/lemans/stores/fs.rb +16 -4
- data/lib/lemans/trial/patch.rb +21 -0
- data/lib/lemans/trial/setup.rb +1 -0
- data/lib/lemans/trial.rb +109 -41
- data/lib/lemans/version.rb +1 -1
- data/lib/lemans.rb +2 -0
- data/lib/miniswen/agent.rb +65 -18
- data/lib/miniswen/cli.rb +20 -4
- data/lib/miniswen/environment/docker.rb +1 -1
- data/lib/miniswen/jail/proxy.rb +62 -0
- data/lib/miniswen/jail.rb +36 -9
- data/lib/miniswen/local.rb +6 -7
- data/lib/miniswen/testing.rb +7 -1
- data/lib/miniswen/version.rb +1 -1
- metadata +49 -1
data/lib/miniswen/testing.rb
CHANGED
|
@@ -36,7 +36,13 @@ module Miniswen
|
|
|
36
36
|
modalities: { input: %w[text], output: %w[text] }
|
|
37
37
|
)
|
|
38
38
|
|
|
39
|
-
|
|
39
|
+
FREE_MODEL = RubyLLM::Model::Info.new(
|
|
40
|
+
id: "test-free", name: "Test free", provider: "openrouter",
|
|
41
|
+
capabilities: %w[function_calling],
|
|
42
|
+
modalities: { input: %w[text], output: %w[text] }
|
|
43
|
+
)
|
|
44
|
+
|
|
45
|
+
MODELS = { PRICED_MODEL.id => PRICED_MODEL, UNPRICED_MODEL.id => UNPRICED_MODEL, FREE_MODEL.id => FREE_MODEL }.freeze
|
|
40
46
|
|
|
41
47
|
# Serves the test models from ruby_llm's registry lookups.
|
|
42
48
|
module FindTestModels
|
data/lib/miniswen/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: lemans
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.
|
|
4
|
+
version: 1.5.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Svyatoslav Kryukov
|
|
@@ -95,6 +95,34 @@ dependencies:
|
|
|
95
95
|
- - "~>"
|
|
96
96
|
- !ruby/object:Gem::Version
|
|
97
97
|
version: '1.1'
|
|
98
|
+
- !ruby/object:Gem::Dependency
|
|
99
|
+
name: rack
|
|
100
|
+
requirement: !ruby/object:Gem::Requirement
|
|
101
|
+
requirements:
|
|
102
|
+
- - "~>"
|
|
103
|
+
- !ruby/object:Gem::Version
|
|
104
|
+
version: '3.1'
|
|
105
|
+
type: :runtime
|
|
106
|
+
prerelease: false
|
|
107
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
108
|
+
requirements:
|
|
109
|
+
- - "~>"
|
|
110
|
+
- !ruby/object:Gem::Version
|
|
111
|
+
version: '3.1'
|
|
112
|
+
- !ruby/object:Gem::Dependency
|
|
113
|
+
name: rackup
|
|
114
|
+
requirement: !ruby/object:Gem::Requirement
|
|
115
|
+
requirements:
|
|
116
|
+
- - "~>"
|
|
117
|
+
- !ruby/object:Gem::Version
|
|
118
|
+
version: '2.2'
|
|
119
|
+
type: :runtime
|
|
120
|
+
prerelease: false
|
|
121
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
122
|
+
requirements:
|
|
123
|
+
- - "~>"
|
|
124
|
+
- !ruby/object:Gem::Version
|
|
125
|
+
version: '2.2'
|
|
98
126
|
- !ruby/object:Gem::Dependency
|
|
99
127
|
name: rexml
|
|
100
128
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -137,6 +165,20 @@ dependencies:
|
|
|
137
165
|
- - "~>"
|
|
138
166
|
- !ruby/object:Gem::Version
|
|
139
167
|
version: '1.5'
|
|
168
|
+
- !ruby/object:Gem::Dependency
|
|
169
|
+
name: webrick
|
|
170
|
+
requirement: !ruby/object:Gem::Requirement
|
|
171
|
+
requirements:
|
|
172
|
+
- - "~>"
|
|
173
|
+
- !ruby/object:Gem::Version
|
|
174
|
+
version: '1.9'
|
|
175
|
+
type: :runtime
|
|
176
|
+
prerelease: false
|
|
177
|
+
version_requirements: !ruby/object:Gem::Requirement
|
|
178
|
+
requirements:
|
|
179
|
+
- - "~>"
|
|
180
|
+
- !ruby/object:Gem::Version
|
|
181
|
+
version: '1.9'
|
|
140
182
|
- !ruby/object:Gem::Dependency
|
|
141
183
|
name: zeitwerk
|
|
142
184
|
requirement: !ruby/object:Gem::Requirement
|
|
@@ -159,6 +201,7 @@ email:
|
|
|
159
201
|
executables:
|
|
160
202
|
- lemans
|
|
161
203
|
- lemans-remote
|
|
204
|
+
- lemans-viewer
|
|
162
205
|
extensions: []
|
|
163
206
|
extra_rdoc_files: []
|
|
164
207
|
files:
|
|
@@ -167,6 +210,7 @@ files:
|
|
|
167
210
|
- README.md
|
|
168
211
|
- exe/lemans
|
|
169
212
|
- exe/lemans-remote
|
|
213
|
+
- exe/lemans-viewer
|
|
170
214
|
- lib/lemans.rb
|
|
171
215
|
- lib/lemans/agent.rb
|
|
172
216
|
- lib/lemans/agents.rb
|
|
@@ -213,6 +257,9 @@ files:
|
|
|
213
257
|
- lib/lemans/environments/daytona/shell.rb
|
|
214
258
|
- lib/lemans/environments/daytona/snapshot_store.rb
|
|
215
259
|
- lib/lemans/environments/docker.rb
|
|
260
|
+
- lib/lemans/environments/docker/proxy/Dockerfile
|
|
261
|
+
- lib/lemans/environments/docker/proxy/README.md
|
|
262
|
+
- lib/lemans/environments/docker/proxy/server.rb
|
|
216
263
|
- lib/lemans/ext/deep_merge.rb
|
|
217
264
|
- lib/lemans/result.rb
|
|
218
265
|
- lib/lemans/runner.rb
|
|
@@ -237,6 +284,7 @@ files:
|
|
|
237
284
|
- lib/miniswen/environment.rb
|
|
238
285
|
- lib/miniswen/environment/docker.rb
|
|
239
286
|
- lib/miniswen/jail.rb
|
|
287
|
+
- lib/miniswen/jail/proxy.rb
|
|
240
288
|
- lib/miniswen/local.rb
|
|
241
289
|
- lib/miniswen/ruby_llm.rb
|
|
242
290
|
- lib/miniswen/testing.rb
|