GPT-5.1-Codex and a rearranging the OpenAI models sections#1146
GPT-5.1-Codex and a rearranging the OpenAI models sections#1146aozherelyeva merged 4 commits intodevelopfrom
Conversation
Qodana for JVM1191 new problems were found
@@ Code coverage @@
+ 71% total lines covered
16421 lines analyzed, 11800 lines covered
# Calculated according to the filters of your coverage tool☁️ View the detailed Qodana report Contact Qodana teamContact us at [email protected]
|
f9d1799 to
583d902
Compare
Qodana for JVM1156 new problems were found
@@ Code coverage @@
+ 72% total lines covered
16693 lines analyzed, 12129 lines covered
# Calculated according to the filters of your coverage tool☁️ View the detailed Qodana report Contact Qodana teamContact us at [email protected]
|
devcrocod
left a comment
There was a problem hiding this comment.
thanks for your pr
Place the newest reasoning models out of the Chat section.
I have some concerns about how the models are currently grouped.
Originally, the grouping was based on OpenAI official documentation, but in later releases OpenAI moved away from that structure: https://platform.openai.com/docs/models.
In practice, all new models starting from GPT5 are reasoning models, which makes it increasingly difficult for us to maintain the existing categorization.
I’d suggest keeping only a high-level grouping: chat, audio, moderation, and embedding.
583d902 to
885a374
Compare
|
@devcrocod good point! Done |
…t for reasoning-capable LLM profiles; place the newest reasoning models out of the Chat section; update docs and tests.
…ate references, tests, and documentation accordingly.
bd981f2 to
7c75e2f
Compare
…"CostOptimized" to "Chat"
7c75e2f to
eaa216f
Compare
…imized" to "Chat".
<!-- Thank you for opening a pull request! Please add a brief description of the proposed change here. Also, please tick the appropriate points in the checklist below. --> ## Motivation and Context <!-- Why is this change needed? What problem does it solve? --> [KG-562](https://youtrack.jetbrains.com/issue/KG-562) Add GPT-5.1-Codex profile 1. Add GPT-5.1-Codex to the OpenAI models. 2. Add NONE as a reasoning effort for reasoning-capable LLM profiles. 3. Place the newest reasoning models out of the Chat section. 4. Update docs and tests. Sources of truth: - https://platform.openai.com/docs/api-reference/responses/create - https://platform.openai.com/docs/models/gpt-5.1-codex ## Breaking Changes <!-- Will users need to update their code or configurations? --> GPT-5-Codex and GPT-5.1 LLM profiles now belong not to Chat but to the Reasoning section. --- #### Type of the changes - [x] New feature (non-breaking change which adds functionality) - [ ] Bug fix (non-breaking change which fixes an issue) - [x] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Tests improvement - [ ] Refactoring #### Checklist - [x] The pull request has a description of the proposed change - [x] I read the [Contributing Guidelines](https://github.com/JetBrains/koog/blob/main/CONTRIBUTING.md) before opening the pull request - [x] The pull request uses **`develop`** as the base branch - [x] Tests for the changes have been added - [x] All new and existing tests passed ##### Additional steps for pull requests adding a new feature - [x] An issue describing the proposed change exists - [x] The pull request includes a link to the issue - [x] The change was discussed and approved in the issue - [x] Docs have been added / updated
<!-- Thank you for opening a pull request! Please add a brief description of the proposed change here. Also, please tick the appropriate points in the checklist below. --> ## Motivation and Context <!-- Why is this change needed? What problem does it solve? --> [KG-562](https://youtrack.jetbrains.com/issue/KG-562) Add GPT-5.1-Codex profile 1. Add GPT-5.1-Codex to the OpenAI models. 2. Add NONE as a reasoning effort for reasoning-capable LLM profiles. 3. Place the newest reasoning models out of the Chat section. 4. Update docs and tests. Sources of truth: - https://platform.openai.com/docs/api-reference/responses/create - https://platform.openai.com/docs/models/gpt-5.1-codex ## Breaking Changes <!-- Will users need to update their code or configurations? --> GPT-5-Codex and GPT-5.1 LLM profiles now belong not to Chat but to the Reasoning section. --- #### Type of the changes - [x] New feature (non-breaking change which adds functionality) - [ ] Bug fix (non-breaking change which fixes an issue) - [x] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Tests improvement - [ ] Refactoring #### Checklist - [x] The pull request has a description of the proposed change - [x] I read the [Contributing Guidelines](https://github.com/JetBrains/koog/blob/main/CONTRIBUTING.md) before opening the pull request - [x] The pull request uses **`develop`** as the base branch - [x] Tests for the changes have been added - [x] All new and existing tests passed ##### Additional steps for pull requests adding a new feature - [x] An issue describing the proposed change exists - [x] The pull request includes a link to the issue - [x] The change was discussed and approved in the issue - [x] Docs have been added / updated
Motivation and Context
KG-562 Add GPT-5.1-Codex profile
Sources of truth:
Breaking Changes
GPT-5-Codex and GPT-5.1 LLM profiles now belong not to Chat but to the Reasoning section.
Type of the changes
Checklist
developas the base branchAdditional steps for pull requests adding a new feature