feat(aws-bedrock/global.openai.gpt-5.6-luna): add new models [bot] - #2200
feat(aws-bedrock/global.openai.gpt-5.6-luna): add new models [bot]#2200models-bot[bot] wants to merge 3 commits into
Conversation
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
|
/test-models |
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 2 potential issues.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit 5e54ca8. Configure here.
| supportedModes: | ||
| - chat | ||
| - responses | ||
| thinking: true |
There was a problem hiding this comment.
Inherited max tokens cap too low
High Severity
limits advertise 128000 max output, but this file never overrides max_tokens. Provider default.yaml therefore keeps maxValue: 2048, so callers inherit a cap far below what global.openai.gpt-5.6-luna actually supports.
Reviewed by Cursor Bugbot for commit 5e54ca8. Configure here.
| - tool_choice | ||
| - system_messages | ||
| - json_output | ||
| - prompt_caching |
There was a problem hiding this comment.
Missing structured output feature
Medium Severity
features omits structured_output even though sibling GPT-5.6 Luna configs (openai, Azure, Databricks, and aws-bedrock-mantle) declare it and this model lists responses in supportedModes.
Reviewed by Cursor Bugbot for commit 5e54ca8. Configure here.
…d reasoning_effort param
|
/test-models |
1 participant
Auto-generated by model-addition-agent for
aws-bedrock/global.openai.gpt-5.6-luna.Note
Low Risk
Catalog-only YAML for a new Bedrock model; no runtime, auth, or billing-code changes.
Overview
Adds Bedrock model catalog entry
global.openai.gpt-5.6-lunawith per-region token costs (including cache and cumulative tiered pricing from 272k tokens), a ~1.05M context window, chat/responses modes, thinking, andreasoning_effort.Supports text/image input, tools, JSON output, and prompt caching as serverless.
Reviewed by Cursor Bugbot for commit e1531eb. Bugbot is set up for automated code reviews on this repo. Configure here.