v0.2.0: support for codex models, better defaults, faster GPT-5#1
Merged
v0.2.0: support for codex models, better defaults, faster GPT-5#1
Conversation
- Add supported_endpoints field to CopilotAuth for endpoint routing - Implement generate_via_responses() for models that only support /responses API - Filter models by policy.state == 'enabled' in addition to model_picker_enabled - Improve error message for HTTP 400 with link to enable models - Improve base prompt for better commit message generation - Better error message when credentials not found
- Add --diff-file <path> to read diff from file or stdin (use - for stdin) - Add --model <name> to override model without persisting to config - Increase diff context to 12 lines (-U12) for better commit messages - Add derive_diff_stat() to generate stat summary from diff content - Add read_diff_from_file() for reading diff from file/stdin - Add hint about enabling models in 'ghcc models' output
- Wrap --diff-file and --model options with #[cfg(debug_assertions)] - Wrap read_diff_from_file() and derive_diff_stat() in debug builds only - Debug build: includes testing options for benchmarking - Release build: clean CLI without testing-only features
- Change default model from gpt-5-mini to gpt-4.1 (best free model) - Update -d/--detailed to use prose paragraphs instead of bullet lists - Update -a/--auto to use prose when body is included - Update README with new default and model recommendations
prankstr
changed the title
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
New Features
gpt-5.1-codexnow work via the/responsesAPI endpointreasoning_effort: "none"for gpt-5/gpt-5.1/gpt-5.2, reducing response time while still maintaining qualityImprovements
gpt-5-minitogpt-4.1- faster and with same-ish quality among free models-dand-amodes now generate small paragraphs to provide context instead of bullet lists