ace-llm-providers-cli 0.33.0 → 0.34.0

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 CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: 7410921d087bbcfa634cec60984b2d578de92d92d84fc0730aa4cae054848b4b
4
- data.tar.gz: '08b71084f7f13ac67941da17c20e84b34c1dd52673f037a929ac7e896e0c2310'
3
+ metadata.gz: 6a2381e3344c0e1e229d1a2594761f92eec1f8af7bee3950bbccd6edd06edd34
4
+ data.tar.gz: 60e39f3cc0468a797a75affc1254703c99f6b49dd41cba8c1f8f141fe2654b01
5
5
  SHA512:
6
- metadata.gz: 92613d00db61f1ad8e8a1e99285c478526b38dd998bd26355a543939ba2453da13f23df97479ae9a4186653fce4b31bd4383dc8fa23ff69c9a887ede90d8c339
7
- data.tar.gz: 50d6485baf304a089b0311a3f0fe096fc90bb697a1b72b4c43f27d295a21631753e1e1d8be718c89722a71e51d3cbfa296926d49fe46875844d4dd53b4969e0a
6
+ metadata.gz: df4f6c5788a4a461ce1dab3be11ba0c9644c584308f6d553d28a3c97ec4e2248fa9a936765815cf4c64407cd37ec9d11b2e6a054459a7aa924c7b391dd7d9d2a
7
+ data.tar.gz: af0ccb22aee51c204e5ec9c932c41e6a1f2369e75574511175f0d939fcedf8ec0c24acfe305ddf2a4fc2622a5c41981b2a26359711538b2f8371971418ce21d3
@@ -1,26 +1,56 @@
1
1
  name: codex
2
- last_synced: 2026-04-23
2
+ last_synced: 2026-04-24
3
3
  class: Ace::LLM::Providers::CLI::CodexClient
4
4
  gem: ace-llm-providers-cli
5
5
  models_dev_id: openai
6
- context_limit: 1050000
7
6
  models:
8
- - gpt-5.3-chat-latest
9
- - gpt-5.3-codex
10
- - gpt-5.3-codex-spark
11
- - gpt-5.4
12
- - gpt-5.4-mini
13
- - gpt-5.4-nano
14
- - gpt-5.4-pro
7
+ - gpt-5.6-terra
8
+ - gpt-6-astra
9
+ - gpt-5.6-sol
10
+ - gpt-5.6-luna
11
+ - gpt-5.3-chat-latest
12
+ - gpt-5.3-codex
13
+ - gpt-5.3-codex-spark
14
+ - gpt-5.4
15
+ - gpt-5.4-mini
16
+ - gpt-5.4-nano
17
+ - gpt-5.4-pro
18
+ limits:
19
+ models:
20
+ gpt-5.3-chat-latest:
21
+ context: 128000
22
+ output: 16384
23
+ gpt-5.3-codex:
24
+ context: 400000
25
+ output: 128000
26
+ gpt-5.3-codex-spark:
27
+ context: 128000
28
+ output: 32000
29
+ gpt-5.4:
30
+ context: 1050000
31
+ output: 128000
32
+ gpt-5.4-mini:
33
+ context: 400000
34
+ output: 128000
35
+ gpt-5.4-nano:
36
+ context: 400000
37
+ output: 128000
38
+ gpt-5.4-pro:
39
+ context: 1050000
40
+ output: 128000
15
41
  aliases:
16
42
  model:
17
- gpt: gpt-5.4
18
- codex: gpt-5.3-codex
43
+ astra: gpt-6-astra
44
+ sol: gpt-5.6-sol
45
+ terra: gpt-5.6-terra
46
+ luna: gpt-5.6-luna
47
+ gpt: gpt-5.6-terra
48
+ codex: gpt-5.6-terra
49
+ mini: gpt-5.6-luna
19
50
  spark: gpt-5.3-codex-spark
20
- mini: gpt-5.4-mini
21
51
  capabilities:
22
- - text_generation
23
- - code_generation
24
- - function_calling
52
+ - text_generation
53
+ - code_generation
54
+ - function_calling
25
55
  default_options:
26
56
  temperature: 0.7
data/CHANGELOG.md CHANGED
@@ -7,6 +7,17 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
7
7
 
8
8
  ## [Unreleased]
9
9
 
10
+ ## [0.34.0] - 2026-09-13
11
+
12
+ ### Changed
13
+
14
+ - Register Codex Astra, Sol, Terra and Luna with Terra as the generic default and Luna as mini; retain all existing explicit IDs and omit unverified new-model limits.
15
+ - Derive Codex client defaults and model listings from provider configuration instead of a separate hardcoded catalog.
16
+
17
+ ### Technical
18
+
19
+ - Isolate subprocess cleanup test fixtures from login-shell startup while retaining timeout and descendant-termination assertions.
20
+
10
21
  ### Fixed
11
22
  - Hardened `SafeCapture` process group termination for container PID namespaces where background processes reparent to PID 1, ensuring reliable cleanup of descendant processes without ESRCH failures.
12
23
 
@@ -30,11 +30,9 @@ module Ace
30
30
  "codex"
31
31
  end
32
32
 
33
- # Default model (can be overridden by config)
34
- DEFAULT_MODEL = "gpt-5.4"
35
-
36
33
  def initialize(model: nil, **options)
37
- @model = model || DEFAULT_MODEL
34
+ @model = model || Ace::LLM::Molecules::ClientRegistry.new.models_for_provider("codex").first
35
+ raise Ace::LLM::ConfigurationError, "No default model configured for codex" if @model.to_s.empty?
38
36
  # Skip normal BaseClient initialization that requires API key
39
37
  @options = options
40
38
  @generation_config = options[:generation_config] || {}
@@ -72,14 +70,7 @@ module Ace
72
70
 
73
71
  # List available Codex models
74
72
  def list_models
75
- # Return models based on what the CLI supports
76
- # Actual models come from YAML config
77
- [
78
- {id: "gpt-5.3-codex", name: "GPT-5.3 Codex", description: "Code-specialized Codex model", context_size: 128_000},
79
- {id: "gpt-5.3-codex-spark", name: "GPT-5.3 Codex Spark", description: "Faster Codex model", context_size: 128_000},
80
- {id: "gpt-5.4", name: "GPT-5.4", description: "Advanced Codex model", context_size: 128_000},
81
- {id: "gpt-5.4-mini", name: "GPT-5.4 Mini", description: "Smaller, faster Codex model", context_size: 128_000}
82
- ]
73
+ Ace::LLM::Molecules::ClientRegistry.new.models_for_provider("codex").map { |id| {id: id, name: id} }
83
74
  end
84
75
 
85
76
  def interactive_supported?
@@ -4,7 +4,7 @@ module Ace
4
4
  module LLM
5
5
  module Providers
6
6
  module CLI
7
- VERSION = "0.33.0"
7
+ VERSION = "0.34.0"
8
8
  end
9
9
  end
10
10
  end
metadata CHANGED
@@ -1,13 +1,13 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: ace-llm-providers-cli
3
3
  version: !ruby/object:Gem::Version
4
- version: 0.33.0
4
+ version: 0.34.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Michal Czyz
8
8
  bindir: exe
9
9
  cert_chain: []
10
- date: 2026-09-05 00:00:00.000000000 Z
10
+ date: 2026-09-13 00:00:00.000000000 Z
11
11
  dependencies:
12
12
  - !ruby/object:Gem::Dependency
13
13
  name: ace-llm