chore(release): bump version to 1.45.0 (minor) - #10750
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b6f106b962
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
sync with openai docs sync re-generate canonical models
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: fbafa02ff1
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| Some("google-vertex/claude-3.5-haiku".to_string()) | ||
| ); | ||
| assert_eq!( | ||
| map_to_canonical_model("gcp_vertex_ai", "claude-sonnet-4-5@20250929", r), |
There was a problem hiding this comment.
For GCP Vertex's static inventory, KNOWN_MODELS still returns claude-3-5-haiku@20241022 (crates/goose/src/providers/formats/gcpvertexai.rs:64-74), but this change deletes both its google-vertex/claude-3.5-haiku record and the mapping regression assertion. Provider::fetch_recommended_models discards any supported model for which map_to_canonical_model returns None (crates/goose-provider-types/src/base.rs:472-478), so this advertised model is now omitted from the recommended-model picker; when configured manually, it also no longer receives canonical context/output limits. Restore its canonical record, or remove it from the provider's supported inventory in the same change.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 4b7eab53d1
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| "context": 400000, | ||
| "output": 128000 | ||
| } | ||
| }, | ||
| { | ||
| "id": "openai/gpt-5-mini", |
There was a problem hiding this comment.
Fresh evidence beyond the earlier OpenAI-list issue is that the unchanged CODEX_KNOWN_MODELS in crates/goose/src/providers/codex.rs:30-35 still advertises gpt-5.2-codex, gpt-5.1-codex-max, and gpt-5.1-codex-mini, with the first also remaining the provider default. For provider name codex, canonical mapping infers the openai namespace, so deleting these records makes fetch_recommended_models filter out three of its four supported models and removes their canonical limits; model pickers consequently show only gpt-5.2 unless users manually enter an unlisted model. Restore these canonical records or update the Codex provider's inventory and default in the same change.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
we do flag that provider as deprecated,
1 participant
Bumps version to 1.45.0.
Please follow these steps:
release/1.45.0PR will be created automatically.